Compare commits

..
Author SHA1 Message Date
Rory Flynn 30ebf3d9af Update version.py 2026-07-29 13:54:39 +02:00
175 changed files with 2326 additions and 14425 deletions

No files matched your search

+1 -1
View File
@@ -11,7 +11,7 @@ jobs:
name: Add issue to project
runs-on: ubuntu-latest
steps:
- uses: actions/add-to-project@v2
- uses: actions/add-to-project@v0.5.0
with:
# You can target a project in a different organization
# to the issue
+3 -3
View File
@@ -11,13 +11,13 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@v7
uses: actions/checkout@v6
- name: Setup Python
uses: actions/setup-python@v7
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Install uv
uses: astral-sh/setup-uv@v10.0.0
uses: astral-sh/setup-uv@v7
with:
enable-cache: true
- name: Install Dependencies
+6 -11
View File
@@ -36,12 +36,10 @@ jobs:
tag-suffix: "-android"
steps:
- name: Checkout repository
uses: actions/checkout@v7
with:
fetch-depth: 0 # the package version comes from the git tags
uses: actions/checkout@v6
# Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
- name: Log in to the Container registry
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
@@ -49,7 +47,7 @@ jobs:
# This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
flavor: |
@@ -61,24 +59,21 @@ jobs:
type=raw,enable=${{ github.ref_type == 'tag' }},value=${{ github.ref_name }},suffix=${{ matrix.platform.tag-suffix }}
type=sha,suffix=${{ matrix.platform.tag-suffix }}
type=sha,format=long,suffix=${{ matrix.platform.tag-suffix }}
# Register emulators so Buildx can build the ARM64 images on the AMD64 runner.
- name: Set up QEMU
uses: docker/setup-qemu-action@v4
# This step sets up some additional capabilities to generate the provenance and sbom attestations
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
# This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
# It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
# It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
- name: Build and push Docker image
id: push
uses: docker/build-push-action@v7
uses: docker/build-push-action@v6
with:
file: ${{ matrix.platform.dockerfile }}
context: .
platforms: linux/amd64,linux/arm64
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
provenance: mode=max
sbom: true
-45
View File
@@ -1,45 +0,0 @@
name: Release
on:
schedule:
- cron: "0 9 * * 1" # Mondays, 09:00 UTC
workflow_dispatch:
push:
tags: ["v*"]
jobs:
tag:
if: github.ref_type != 'tag'
runs-on: ubuntu-latest
permissions:
contents: write
actions: write
env:
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@v7
with:
fetch-depth: 0
- run: |
last=$(git describe --tags --abbrev=0 --match 'v*')
if [ "$(git rev-list "$last..HEAD" --count)" = 0 ]; then
echo "Nothing merged since $last"; exit 0
fi
tag=v$(date -u +%Y.%-m.%-d)
gh release create "$tag" --target "$GITHUB_SHA" --generate-notes
# Events made with GITHUB_TOKEN don't start other workflows; run them by hand.
gh workflow run release.yml --ref "$tag"
gh workflow run publish-release-docker.yml --ref "$tag"
publish:
if: github.ref_type == 'tag'
runs-on: ubuntu-latest
environment: pypi # only tag refs may deploy; the PyPI trusted publisher requires it
permissions:
id-token: write # PyPI trusted publishing
steps:
- uses: actions/checkout@v7
with:
fetch-depth: 0
- uses: astral-sh/setup-uv@v10.0.0
- run: uv build && uv publish
+3 -3
View File
@@ -12,13 +12,13 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@v7
uses: actions/checkout@v6
- name: Setup Python
uses: actions/setup-python@v7
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Install uv
uses: astral-sh/setup-uv@v10.0.0
uses: astral-sh/setup-uv@v7
with:
enable-cache: true
- name: Install Dependencies
+7 -22
View File
@@ -5,10 +5,6 @@ on:
pull_request:
branches: [ main ]
permissions:
contents: read
pull-requests: write # coverage comment
jobs:
build:
name: Run Python Tests
@@ -17,40 +13,29 @@ jobs:
fail-fast: false
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13', '3.14']
env:
# Takes precedence over .python-version, which otherwise makes `uv run`
# rebuild the venv with 3.10 and test every matrix entry on 3.10.
UV_PYTHON: ${{ matrix.python-version }}
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Install uv
uses: astral-sh/setup-uv@v10.0.0
uses: astral-sh/setup-uv@v7
with:
enable-cache: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v7
uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python-version }}
- name: Install Python dependencies
run: |
uv sync --locked --group dev
uv sync --locked --group dev --python ${{ matrix.python-version }}
- name: Test with pytest
run: |
set -o pipefail
make test-ci | tee pytest-coverage.txt
- name: Coverage job summary
run: uv run coverage report --format=markdown --show-missing --skip-covered >> "$GITHUB_STEP_SUMMARY"
- name: Pytest coverage comment
# One comment per PR, not one per matrix entry. PRs from forks get a
# read-only token and can't post; the job summary above still works.
if: github.event_name == 'pull_request' && matrix.python-version == '3.13'
continue-on-error: true
uses: MishaKav/pytest-coverage-comment@v1.12.2
continue-on-error: true # Workflows running on a fork can't post comments
uses: MishaKav/pytest-coverage-comment@main
if: github.event_name == 'pull_request'
with:
pytest-coverage-path: ./pytest-coverage.txt
junitxml-path: ./pytest.xml
# The full table with per-line links exceeds GitHub's 65536-char comment limit.
report-only-changed-files: true
remove-links-to-lines: true
+3 -5
View File
@@ -11,12 +11,10 @@ jobs:
update-ios-version:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
- name: Install script dependencies
run: python -m pip install "packaging==26.3"
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
- name: Run script to fetch latest iOS releases from Apple RSS feed.
run: python .github/workflows/scripts/update-ios-releases.py
run: python3 .github/workflows/scripts/update-ios-releases.py
- name: Create Pull Request
uses: peter-evans/create-pull-request@v8
with:
+2 -14
View File
@@ -119,24 +119,12 @@ ARG DEBIAN_FRONTEND=noninteractive
RUN apt-get update \
&& apt-get install -y \
adb \
binutils \
default-jre-headless \
file \
git \
jq \
less \
libcurl4 \
libimage-exiftool-perl \
libssl3 \
libusb-1.0-0 \
moreutils \
p7zip-full \
python3 \
ripgrep \
sqlite3 \
tree \
unzip \
xxd
sqlite3
COPY --from=build-libplist /build /
COPY --from=build-libimobiledevice-glue /build /
COPY --from=build-libtatsu /build /
@@ -156,7 +144,7 @@ ADD --checksum=sha256:a20e07f8b2ea47620aff0267f230c3f1f495f097081fd709eec51cf2a2
RUN echo 'alias abe="java -jar /opt/abe/abe.jar"' >> ~/.bashrc
# Generate adb key folder
RUN echo 'if [ ! -f /root/.android/adbkey ]; then adb keygen /root/.android/adbkey > /dev/null 2>&1; fi' >> ~/.bashrc
RUN echo 'if [ ! -f /root/.android/adbkey ]; then adb keygen /root/.android/adbkey 2&>1 > /dev/null; fi' >> ~/.bashrc
RUN mkdir /root/.android
# Setup investigations environment
+1 -1
View File
@@ -31,7 +31,7 @@ ADD --checksum=sha256:a20e07f8b2ea47620aff0267f230c3f1f495f097081fd709eec51cf2a2
RUN echo 'alias abe="java -jar /opt/abe/abe.jar"' >> ~/.bashrc
# Generate adb key folder
RUN echo 'if [ ! -f /root/.android/adbkey ]; then adb keygen /root/.android/adbkey > /dev/null 2>&1; fi' >> ~/.bashrc
RUN echo 'if [ ! -f /root/.android/adbkey ]; then adb keygen /root/.android/adbkey 2&>1 > /dev/null; fi' >> ~/.bashrc
RUN mkdir /root/.android
ENTRYPOINT [ "/usr/local/bin/mvt-android" ]
-4
View File
@@ -1,4 +0,0 @@
prune tests
prune docs
prune .github
exclude uv.lock Dockerfile* mkdocs.yml .readthedocs.yaml .safety-policy.yml .python-version .gitignore Makefile
+5
View File
@@ -32,3 +32,8 @@ clean:
dist:
$(UV) build
upload:
$(UV) tool run twine upload dist/*
test-upload:
$(UV) tool run twine upload --repository testpypi dist/*
+10 -14
View File
@@ -58,33 +58,29 @@ For alternative installation options and known issues, please refer to the [docu
## Usage
MVT provides three commands: `mvt-ios` and `mvt-android` analyse acquisitions from devices of that platform, and `mvt` hosts what belongs to neither: `version`, `completion`, `plugins` and `download-iocs` (`version` and `download-iocs` remain available on the platform commands for now). Running `mvt` on its own shows the installed version, update notices and the available commands. [Check out the documentation to learn how to use them!](https://docs.mvt.re/)
Pass `--verbose` to any of the three commands, before the command name (`mvt-ios --verbose check-backup ...`), for debug output. The `--verbose` option the `check-*` commands accept after their name still works but is kept for compatibility only and will be removed in a future release.
MVT provides two commands `mvt-ios` and `mvt-android`. [Check out the documentation to learn how to use them!](https://docs.mvt.re/)
### Shell completion
MVT can generate a shell completion script for Bash, Zsh, and Fish which covers `mvt`, `mvt-ios` and `mvt-android`:
MVT can generate shell completion scripts for Bash, Zsh, and Fish:
```bash
mvt completion
mvt-ios completion
mvt-android completion
```
The command prints setup instructions by default. To generate the completion script directly, pass the shell name:
The commands print setup instructions by default. To generate a completion script directly, pass the shell name:
```bash
mvt completion bash
mvt-ios completion bash
mvt-android completion zsh
```
MVT only writes completion files or shell configuration when `--install` is passed. See the [command completion documentation](https://docs.mvt.re/en/latest/command_completion/) for details.
Plugin packages extend MVT with additional forensic modules, which run inside
the `check-*` commands, and with top-level commands on `mvt`, `mvt-ios` and
`mvt-android`. See the
Module-running `check-*` commands can load custom Python modules with
`--load-module PATH` or from a folder set in `MVT_CUSTOM_MODULES`. See the
[development documentation](https://docs.mvt.re/en/latest/development/) for
writing and installing them, and the
[custom CLI command documentation](https://docs.mvt.re/en/latest/development/custom_commands/)
for the entry points a package registers commands in.
details.
## License
-6
View File
@@ -57,9 +57,3 @@ If the backup is encrypted, ABE will prompt you to enter the password.
Alternatively, [ab-decrypt](https://github.com/joernheissler/ab-decrypt) can be used for that purpose.
You can then extract SMSs with MVT by passing the folder path as parameter instead of the `.ab` file: `mvt-android check-backup --output /path/to/results/ /path/to/backup/` (the path to backup given should be the folder containing the `apps` folder).
When an output folder is specified, URLs extracted from SMS and MMS messages
are also written to `urls.json`. Each entry contains the URL, its expanded
destination when MVT resolved a shortened URL during indicator checking, the
message timestamp, and the `sms` source. The same file is created by
`check-androidqf` when its nested Android backup contains messages with URLs.
+1 -1
View File
@@ -58,7 +58,7 @@ mvt-android check-intrusion-logs --output /path/to/results/ /path/to/intrusion-l
| `-l, --list-modules` | List the available intrusion-log modules and exit. |
| `-m, --module NAME` | Run a single module (e.g. `DnsEvent`) instead of all of them. |
| `-t, --timezone TZ` | IANA timezone name for the device (e.g. `Europe/Paris`). When set, event timestamps are converted to the device's local time instead of UTC. |
| `-v, --verbose` | Verbose logging. Kept for compatibility and to be removed in a future release: pass `--verbose` to `mvt-android` itself instead. |
| `-v, --verbose` | Verbose logging. |
## Modules
+22 -22
View File
@@ -6,61 +6,61 @@ Click provides tab completion support for Bash (version 4.4 and up), Zsh, and Fi
To enable it, you need to register a completion script with your shell, which varies depending on the shell you are using.
`mvt completion` generates one script which covers `mvt`, `mvt-ios` and `mvt-android`. The following describes how to generate that script and add it to your shell configuration.
The following describes how to generate the command completion scripts and add them to your shell configuration.
> **Note: You will need to start a new shell for the changes to take effect.**
### For Bash
```bash
# Generate the bash completion script
mvt completion bash > ~/.mvt-complete.bash
# Generate bash completion scripts
mvt-ios completion bash > ~/.mvt-ios-complete.bash
mvt-android completion bash > ~/.mvt-android-complete.bash
```
Add the following to `~/.bashrc`:
```bash
# source the mvt completion script
[ -f ~/.mvt-complete.bash ] && . ~/.mvt-complete.bash
# source mvt completion scripts
[ -f ~/.mvt-ios-complete.bash ] && . ~/.mvt-ios-complete.bash
[ -f ~/.mvt-android-complete.bash ] && . ~/.mvt-android-complete.bash
```
### For Zsh
```bash
# Generate the zsh completion script
mvt completion zsh > ~/.mvt-complete.zsh
# Generate zsh completion scripts
mvt-ios completion zsh > ~/.mvt-ios-complete.zsh
mvt-android completion zsh > ~/.mvt-android-complete.zsh
```
Add the following to `~/.zshrc`:
```bash
# source the mvt completion script
[ -f ~/.mvt-complete.zsh ] && . ~/.mvt-complete.zsh
# source mvt completion scripts
[ -f ~/.mvt-ios-complete.zsh ] && . ~/.mvt-ios-complete.zsh
[ -f ~/.mvt-android-complete.zsh ] && . ~/.mvt-android-complete.zsh
```
### For Fish
```bash
# Generate the fish completion script
mkdir -p ~/.config/fish/conf.d
mvt completion fish > ~/.config/fish/conf.d/mvt-completion.fish
# Generate fish completion scripts
mkdir -p ~/.config/fish/completions
mvt-ios completion fish > ~/.config/fish/completions/mvt-ios.fish
mvt-android completion fish > ~/.config/fish/completions/mvt-android.fish
```
Fish loads the files in `~/.config/fish/conf.d` automatically.
Fish loads completion files from `~/.config/fish/completions` automatically.
### Automatic Installation
MVT can write the completion file and update the relevant shell configuration for Bash and Zsh when you pass `--install`:
```bash
mvt completion bash --install
mvt-ios completion bash --install
mvt-android completion bash --install
```
Replace `bash` with `zsh` or `fish` as needed. For Fish, `--install` writes the completion file into `~/.config/fish/conf.d` and changes no shell configuration.
!!! note
Earlier versions generated one script per command, with `mvt-ios completion`
and `mvt-android completion`. Files written by them keep working. When you
switch to the single script, remove the old files and the lines which load
them from your shell configuration.
Replace `bash` with `zsh` or `fish` as needed. For Fish, `--install` writes the completion file into `~/.config/fish/completions`.
For more information, visit the official [Click Docs](https://click.palletsprojects.com/en/stable/shell-completion/#enabling-completion).
+131
View File
@@ -0,0 +1,131 @@
# Development
The Mobile Verification Toolkit team welcomes contributions of new forensic modules or other contributions which help improve the software.
## Local environment
MVT uses `uv` for dependency management. To install the project and development dependencies from the locked environment, run:
```bash
make install
```
## Testing
MVT uses `pytest` for unit and integration tests. Code style consistency is maintained with `ruff` and `mypy`. All can
be run automatically with:
```bash
make check
```
Run these tests before making new commits or opening pull requests.
## Module dependencies
Modules can require other modules to run first by declaring their classes in
`dependencies`. The command runner uses a stable topological ordering, so the
existing module list order is preserved wherever dependency constraints allow.
```python
class DependentModule(MVTModule):
dependencies = (PrerequisiteModule,)
def run(self):
prerequisite_results = self.get_dependency_results(PrerequisiteModule)
```
Selecting a single module also runs its transitive dependencies. If a dependency
is unavailable or the dependency graph contains a cycle, the command logs a
warning and does not run any modules.
## Custom modules
Module-running `check-*` commands can load custom modules from Python files that
are not installed as part of MVT. Load one file with:
```bash
mvt-ios check-backup --load-module ./example_module.py --output ./out ./backup
```
You can also load a folder. MVT loads non-hidden top-level `*.py` files in
sorted order and skips `__init__.py`:
```bash
mvt-ios check-fs --load-module ./custom_modules ./filesystem-dump
```
Set `MVT_CUSTOM_MODULES` to load a folder for every module-running command. This
folder is loaded before any `--load-module` path:
```bash
MVT_CUSTOM_MODULES=./custom_modules mvt-android check-bugreport ./bugreport.zip
```
Custom modules are normal `MVTModule` subclasses:
```python
from mvt.common.module import MVTModule
class ExampleCustomModule(MVTModule):
supported_commands = (("ios", "check-backup"), ("ios", "check-fs"))
slug = "example_custom_module"
def run(self):
self.results = [{"message": "custom module ran"}]
def check_indicators(self):
pass
def serialize(self, result):
return None
```
Use `supported_commands` to declare the platform/command pairs a module
supports. Empty `supported_commands` means the module will not run and MVT logs
a warning. This explicit declaration is required for every command. Supported
pairs are:
```python
("ios", "check-backup")
("ios", "check-fs")
("ios", "check-iocs")
("ios", "check-sysdiagnose")
("android", "check-backup")
("android", "check-bugreport")
("android", "check-androidqf")
("android", "check-intrusion-logs")
("android", "check-iocs")
```
Custom modules can depend on existing MVT module classes. Dependencies are
resolved with the same ordering logic as built-in modules, and custom modules
are appended after built-ins before ordering:
```python
from mvt.common.module import MVTModule
from mvt.ios.modules.backup.manifest import Manifest
class DependentCustomModule(MVTModule):
supported_commands = (("ios", "check-backup"),)
dependencies = (Manifest,)
def run(self):
manifest_results = self.get_dependency_results(Manifest)
self.results = [{"manifest_entries": len(manifest_results)}]
```
## Profiling
Some MVT modules extract and process significant amounts of data during the analysis process or while checking results against known indicators. Care must be
take to avoid inefficient code paths as we add new modules.
MVT modules can be profiled with Python built-in `cProfile` by setting the `MVT_PROFILE` environment variable.
```bash
MVT_PROFILE=1 dev/mvt-ios check-backup test_backup
```
Open an issue or PR if you are encountering significant performance issues when analyzing a device with MVT.
-202
View File
@@ -1,202 +0,0 @@
# Custom CLI Commands
MVT can load additional top-level commands into `mvt`, `mvt-ios` and
`mvt-android`. A command package chooses which of the three each of its
commands is added to.
Custom commands are different from [custom forensic modules](index.md#custom-modules):
commands add new CLI operations, while modules add analysis steps to existing
`check-*` commands.
!!! warning
Custom commands run as trusted Python code inside the MVT process. Install
or load commands only from sources you trust. MVT does not sandbox
third-party commands, and the MVT maintainers do not maintain them.
## Install a Command Package
Python packages can register a Click command or group on one or more of the MVT CLIs.
A minimal package can expose this command from `my_mvt_plugin.py`:
```python
import click
@click.command()
@click.argument("path", type=click.Path(exists=True))
def summarize(path):
"""Summarize an acquisition."""
click.echo(f"Summarizing {path}")
```
Log through `get_plugin_logger(__name__)` from `mvt.plugin`. Records logged
through `logging.getLogger(__name__)` do not reach `command.log`, and MVT's
console handler does not show them.
Register the object in the package's `pyproject.toml`. The entry-point name is
the command users invoke:
```toml
[project.entry-points."mvt.ios.cli_plugins"]
summarize = "my_mvt_plugin:summarize"
[project.entry-points."mvt.android.cli_plugins"]
summarize = "my_mvt_plugin:summarize"
```
Each entry-point group adds the command to one CLI: `mvt.ios.cli_plugins` to
`mvt-ios`, `mvt.android.cli_plugins` to `mvt-android` and `mvt.cli_plugins` to
`mvt`. Register the command in the group of every CLI which should offer it: a
platform-specific command belongs in one platform group, and a command which
handles acquisitions of both platforms, as above, in both. After installing the
package in the same environment as MVT, the command appears directly in those
CLIs:
```bash
mvt-ios summarize ./ios-backup
mvt-android summarize ./androidqf-output
```
For a `pipx` installation of MVT, inject the plugin into MVT's environment:
```bash
pipx inject mvt my-mvt-plugin
```
When MVT is installed in an active virtual environment, install the plugin with
`pip` in that environment. `mvt plugins list` shows the installed packages and
the commands they add, see [Managing Plugins](plugins.md).
Command packages that need their own settings, such as an API key, should store
them in a namespaced [plugin configuration file](plugin_configuration.md)
rather than in MVT's own `config.yaml`.
### Commands on `mvt`
A MVT plugin command can also add sub-commands to the base `mvt` command. This can be used for commands which are not tied to a particular forensic platform:
```toml
[project.entry-points."mvt.cli_plugins"]
my-plugin = "my_mvt_plugin:my_plugin"
```
Commands in this group are added to `mvt` only, so this one is invoked as
`mvt my-plugin`. A command on `mvt` has nothing but its name to say which
plugin it belongs to, so name it after the plugin, and make it a Click group
when the plugin has several operations to offer, such as
`mvt my-plugin configure`.
## Developing a Command Locally
A package is how a command is distributed. While a command is being written,
MVT can load it straight from its file instead, so the package need not be
reinstalled after every change; an editable install of the package does the
same through its entry points. Create a Python file that exports one Click
command or group named `cli`:
```python
import click
@click.command("case-summary")
@click.argument("path", type=click.Path(exists=True))
def cli(path):
"""Summarize a case directory."""
click.echo(f"Summarizing {path}")
```
Pass the file before the custom command name:
```bash
mvt-ios --load-command ./case_summary.py case-summary ./ios-backup
```
`--load-command` can be repeated and also accepts a folder. MVT loads
non-hidden top-level `*.py` files in sorted order and skips `__init__.py`.
Every loaded file must export one `cli` object.
To load a file or folder on every invocation, set the environment variable of
the CLI the commands belong on. Like the entry-point groups, each variable adds
its commands to one CLI only:
```bash
export MVT_CUSTOM_COMMANDS=./commands
export MVT_IOS_CUSTOM_COMMANDS=./ios_commands
export MVT_ANDROID_CUSTOM_COMMANDS=./android_commands
```
## Building a Module-Running Command
A command which runs forensic modules over an acquisition subclasses `Command`.
`Command` creates the output folder and writes `command.log`. It orders the
modules, resolves their dependencies and runs them. It writes the result files,
`alerts.json` and `info.json`. The subclass sets `platform`, `name` and
`modules`:
```python
from mvt.plugin import Command, MVTModule, convert_unix_to_iso, get_plugin_logger
log = get_plugin_logger(__name__)
class APKManifest(MVTModule):
supported_commands = (("android", "check-apks"),)
def run(self):
self.results = [{"checked_at": convert_unix_to_iso(0)}]
class CmdCheckAPKs(Command):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.platform = "android"
self.name = "check-apks"
self.modules = [APKManifest]
```
`platform` and `name` are the pair the modules declare in
`supported_commands`. `modules` lists the module classes the command runs,
imported directly. A command which runs modules of another plugin depends on
that package in `pyproject.toml` and imports them the same way. `init()`,
`module_init(module)` and `finish()` are optional hooks. `run()` calls them
before the run, before each module and after the run.
Wrap the command in a Click command with an `--output` option. Run it, then
print the alert summary:
```python
import click
@click.command("check-apks")
@click.option("--output", "-o", type=click.Path(exists=False))
@click.argument("TARGET_PATH", type=click.Path(exists=True))
def cli(output, target_path):
cmd = CmdCheckAPKs(target_path=target_path, results_path=output)
log.info("Checking APK files at path: %s", target_path)
cmd.run()
cmd.show_alerts_brief()
```
The `--verbose` option of `mvt`, `mvt-ios` and `mvt-android` applies to the
command. The command defines no `--verbose` option of its own. The pair a
plugin command adds is not listed anywhere in MVT. Name it in the plugin's
README.
## Naming and Errors
Built-in MVT commands cannot be replaced. External command names must also be
unique on each CLI; when installed packages or environment paths collide, MVT
keeps the first command and logs a warning. The environment path of a CLI is
registered before its installed packages, so a command loaded from there wins a
collision with a package. A collision from an explicit `--load-command` is a
usage error.
A package entry point or environment command that cannot be imported appears
as a marked broken command without preventing other MVT commands from working.
Invoke that command to see its package or file source and the underlying error.
An invalid command supplied explicitly with `--load-command` fails immediately
with a usage error.
Installed command packages use the entry-point name as the CLI command name.
The entry point must resolve to a `click.Command` or `click.Group`.
-391
View File
@@ -1,391 +0,0 @@
# Development
The Mobile Verification Toolkit team welcomes contributions of new forensic modules or other contributions which help improve the software.
## Local environment
MVT uses `uv` for dependency management. To install the project and development dependencies from the locked environment, run:
```bash
make install
```
## Testing
MVT uses `pytest` for unit and integration tests. Code style consistency is maintained with `ruff` and `mypy`. All can
be run automatically with:
```bash
make check
```
Run these tests before making new commits or opening pull requests.
## Module dependencies
Modules can require other modules to run first by declaring their classes in
`dependencies`. The command runner uses a stable topological ordering, so the
existing module list order is preserved wherever dependency constraints allow.
```python
class DependentModule(MVTModule):
dependencies = (PrerequisiteModule,)
def run(self):
prerequisite_results = self.get_dependency_results(PrerequisiteModule)
```
Selecting a single module also runs its transitive dependencies.
A module can only depend on modules the command it runs in also has. When a
declared dependency is not among them, the command logs a warning naming the
module and the missing dependency, skips that module and everything depending
on it, and runs the rest of the analysis. Selecting such a module with
`--module` therefore leaves nothing to run, which the warning explains.
A cycle in the dependency graph is a programming error rather than a
configuration problem: the command logs a warning and runs no modules at all.
## Custom modules
MVT's module-running `check-*` commands can run forensic modules which are not
part of MVT. Custom modules are distributed as plugin packages. A Python
package installed next to MVT registers its modules through an entry point.
The modules then load automatically in every command they support, see
[Installed module packages](#installed-module-packages). `mvt plugins list`
shows the installed packages and where each one was installed from.
MVT can also load module files by path, with `--load-module` and
`MVT_CUSTOM_MODULES`, see
[Developing modules locally](#developing-modules-locally). This can be used
while writing a module. Use a Python package to distribute one.
A custom module declares in `supported_commands` the platform and command
pairs it runs in. A module with empty `supported_commands` does not run and
MVT logs a warning. The nine pairs are:
```python
("ios", "check-backup")
("ios", "check-fs")
("ios", "check-iocs")
("ios", "check-sysdiagnose")
("android", "check-backup")
("android", "check-bugreport")
("android", "check-androidqf")
("android", "check-intrusion-logs")
("android", "check-iocs")
```
`check-iocs` re-checks stored results rather than an acquisition. It matches
every `<slug>.json` file in the results folder to the module with that slug.
It then runs that module's `check_indicators()` again. A module which
implements `check_indicators()` is included in `check-iocs` for its platform.
It does not need to declare the `check-iocs` pair.
### Writing a module
A module subclasses `MVTModule` or one of the base classes below and
implements `run()`. `check_indicators()` and `serialize()` are optional. The
first matches results against IOCs or detections. The second returns timeline
records.
```python
from mvt.plugin import IOSExtraction, convert_unix_to_iso
class ExampleCustomModule(IOSExtraction):
supported_commands = (
("ios", "check-backup"),
("ios", "check-fs"),
)
slug = "example_custom_module"
def run(self):
self.results = [{"checked_at": convert_unix_to_iso(0)}]
def check_indicators(self):
pass
def serialize(self, result):
return None
```
The base classes are:
- `MVTModule`: the base of every module. It provides `self.results`,
`self.alertstore`, `self.log`, `self.indicators` and
`get_dependency_results()`. Subclass it directly for a module which reads
only the results of other modules.
- `IOSExtraction`: `("ios", "check-backup")` and `("ios", "check-fs")`. Adds
`_find_ios_database()`, which locates a module's database in a backup or in
a filesystem dump and repairs it if it is malformed. Adds
`_get_backup_files_from_manifest()`, `_get_backup_file_from_id()` and
`_get_fs_files_from_patterns()`. Adds `_open_sqlite_db()`, which opens a
database read-only.
- `SysdiagnoseExtraction`: `("ios", "check-sysdiagnose")`. MVT extracts the
archive and calls `from_sysdiagnose_folder()` before `run()`. The module
reads files with `_get_files_by_pattern()` and `_get_file_content()`.
`ips_files` lists the crash reports. See
[Check an iOS Sysdiagnose](../ios/sysdiagnose.md).
- `AndroidQFModule`: `("android", "check-androidqf")`. MVT calls `from_dir()`
or `from_zip()` with the file list of the acquisition. The module reads
files with `_get_files_by_pattern()` and `_get_file_content()`.
`_get_device_timezone()` returns the device timezone.
- `AndroidBackupModule`: `("android", "check-backup")`. MVT calls `from_dir()`
or `from_ab()`. The module reads files with `_get_files_by_pattern()` and
`_get_file_content()`.
- `BugReportModule`: `("android", "check-bugreport")`. MVT calls `from_dir()`
or `from_zip()`. The module reads files with `_get_files_by_pattern()`,
`_get_files_by_patterns()` and `_get_file_content()`.
`_get_dumpstate_file()` returns the dumpstate file, and
`_get_file_modification_time()` the modification time of a file.
The underscore-named helpers are internal to the base classes. Plugin modules
can call them. Their names and signatures can change between releases. Read
the base class in `src/mvt/ios/modules` or `src/mvt/android/modules` before
relying on one.
### Depending on a built-in module
A module which post-processes records generated by one or more built-in MVT
modules must declare the source modules in `dependencies`. It reads their
results with `get_dependency_results()`. Import the class from its family
package: `mvt.ios.modules.backup`, `mvt.ios.modules.fs`,
`mvt.ios.modules.mixed`, `mvt.android.modules.androidqf`,
`mvt.android.modules.backup`, `mvt.android.modules.bugreport` or
`mvt.android.modules.intrusion_logs`.
```python
from mvt.ios.modules.backup import Manifest
from mvt.plugin import MVTModule
class DependentCustomModule(MVTModule):
supported_commands = (("ios", "check-backup"),)
dependencies = (Manifest,)
def run(self):
manifest_results = self.get_dependency_results(Manifest)
self.results = [{"manifest_entries": len(manifest_results)}]
```
Dependencies are ordered as for the built-in modules, with custom modules
appended after the built-ins, see [Module dependencies](#module-dependencies).
A dependency has to run in every command the module supports. Where it does
not, MVT skips the module with a warning.
`get_dependency_results()` returns the plain dictionaries the module produced.
They are the same records it writes to `<slug>.json`. Typed results per module
are planned.
### Replacing a built-in module
A custom module which extends a built-in one runs alongside it, and when the
two share a slug they write to the same results file. MVT warns about that
collision, naming both modules, where each came from and the file the later one
overwrites, but it runs them both. Set `replaces` to the class the module
supersedes to take that module's place instead: when both are available to a
command, the named module is dropped from the run.
```python
from mvt.ios.modules.backup import Manifest as BuiltinManifest
class Manifest(BuiltinManifest):
supported_commands = (("ios", "check-backup"),)
replaces = BuiltinManifest
```
Keeping the class name of the replaced module, as above, keeps the name
`--module` selects the module by and the slug its results file is named after.
A replacement with a different class name writes to a file named after its own
slug, unless it sets `slug` to the slug of the module it replaces, and
`--module` still selects it by the name of the replaced module, which MVT logs.
Taking over the slug of a replaced module is not a collision and is not warned
about, because that module is no longer part of the run.
Modules which depend on the replaced module receive the replacement instead, so
`get_dependency_results(BuiltinManifest)` returns the replacement's results. A
module must not depend on the module it replaces: that module does not run, so
the replacement has to produce the data itself, and MVT logs a warning when a
module declares both.
A replacement takes on the obligations of the module it replaces. If it
declares a dependency the command does not provide, it is skipped like any
other module with an unavailable dependency, and the module it replaced stays
out of the run: neither of them produces results, and the modules depending on
the replaced module are skipped as well.
Subclassing the replaced module is not required, but a replacement which is not
a subclass is logged with a warning, because its results may not be what the
modules depending on the replaced module expect. Naming a module the command
does not run has no effect, and modules which replace each other in a cycle all
keep running and replace nothing. Every applied substitution is logged, so it
is recorded in `command.log` when the command runs with an `--output` folder.
Every command resolves replacements on its own. `check-iocs` matches stored
results files against the slugs of the modules available for that command. A
replacement which subclasses the module it replaces inherits its
`check_indicators()`. It is then part of `check-iocs` for its platform and
re-checks the results file named after its slug. A replacement with no
`check_indicators()` is not part of `check-iocs`. The built-in module it
replaced re-checks the file. `check-iocs` matches `--module` on the class name
only. Pass a differently named replacement's own name there, not the name of
the module it replaces.
### Importing from MVT
Import from `mvt.plugin` if it has what you need. The names it exports are
kept working on a best-effort basis. A change to one of them is announced in
the release notes. Anything else in `mvt` can be imported too, but may change
between releases without notice. The plugin interface is best effort.
`mvt.plugin` exports the base classes above and `Command`, `Alert` and
`AlertLevel`, the result types, `DatabaseNotFoundError` and
`DatabaseCorruptedError`, the timestamp converters, the settings API of
[Plugin Configuration](plugin_configuration.md), MVT's own `settings`,
`get_plugin_logger()` and `MVT_VERSION`. `src/mvt/plugin.py` holds the list.
Read MVT's `settings` for values such as `NETWORK_ACCESS_ALLOWED` and
`NETWORK_TIMEOUT`. Plugin values go in the plugin's own settings file.
## Installed module packages
Python packages can register modules so they load automatically in every
module-running `check-*` command, without `--load-module` or
`MVT_CUSTOM_MODULES`. Register an entry point in the `mvt.modules` group in
the package's `pyproject.toml`:
```toml
[project.entry-points."mvt.modules"]
mvt-plugin-example-org = "mvt_plugin_example_org:get_modules"
```
The entry point must resolve to an iterable of `MVTModule` subclasses, or to
a callable returning one:
```python
from mvt.plugin import MVTModule
class PackagedModule(MVTModule):
supported_commands = (("ios", "check-backup"),)
def run(self):
self.results = [{"message": "packaged module ran"}]
def get_modules() -> list[type[MVTModule]]:
return [PackagedModule]
```
`get_modules()` is the package's module list, written by hand. A package which
keeps its modules in separate files imports each class there and lists it. A
module missing from the list does not load.
Installed modules follow the same rules as other custom modules: each module
must declare `supported_commands`, and dependencies are resolved with the
standard ordering logic. A broken entry point is skipped with a warning and
does not prevent MVT from running. As with custom commands, installed module
packages run as trusted code inside the MVT process, so install only packages
from sources you trust.
For a `pipx` installation of MVT, inject the package into MVT's environment:
```bash
pipx inject mvt mvt-plugin-example-org
```
Module packages that need their own settings, such as an API key, should store
them in a namespaced [plugin configuration file](plugin_configuration.md)
rather than in MVT's own `config.yaml`.
### Naming module packages
Name module packages `mvt-plugin-<name>` (import package `mvt_plugin_<name>`),
and include the name of the publishing organization or author so packages from
different groups do not collide: for example, an organisation's custom modules
would be distributed as `mvt-plugin-example-org` with the import package
`mvt_plugin_example_org`.
The prefix makes module packages easy to find on PyPI and keeps their import
names from clashing with unrelated Python packages. It is a convention, not a
technical requirement: modules load through the `mvt.modules` entry point
regardless of what the package is called, and existing packages with other
names keep working. Note that the prefix is also not a mark of authenticity —
anyone can publish a package with any available name, so vet a module package
and its publisher before installing it, whatever it is called.
### Module logging
Modules log through `self.log`, and MVT names the logger for where the module
came from. MVT's own modules log under their dotted path (for example
`mvt.ios.modules.mixed.whatsapp`). Everything external is namespaced under
`mvt.ext` to keep it visually distinct from built-in modules and isolated from
MVT's internal logger tree:
- Installed packages log under `mvt.ext.<package>`, with the `mvt_plugin_`
prefix stripped: modules in `mvt_plugin_example_org` log as
`mvt.ext.example_org.*`.
- Files loaded with `--load-module` or `MVT_CUSTOM_MODULES` log as
`mvt.ext.<file name>`.
Outside a module class, for example in a custom command line handler, log
through `get_plugin_logger(__name__)`. It returns a logger in the same
namespace.
## Developing modules locally
While a module is being written, load it from its file. `--load-module` takes a
Python file, or a folder of them, on every module-running command, and can be
repeated:
```bash
mvt-ios check-backup --load-module ./example_module.py --output ./out ./backup
```
For a folder, MVT loads its non-hidden top-level `*.py` files in sorted order
and skips `__init__.py`. `MVT_CUSTOM_MODULES` names a folder to load on every
module-running command, before any `--load-module` path:
```bash
MVT_CUSTOM_MODULES=./custom_modules mvt-android check-bugreport ./bugreport.zip
```
Files loaded this way follow the same rules as packaged modules.
`--list-modules` reports them with the SHA-256 hash of the file in place of a
version. An editable install of the package (`pip install -e .`) also works:
the modules load through the entry point, and `mvt plugins list` shows the
package with the `local` origin.
Loading by path is for development. Move a module into a package once it
works.
## Auditing loaded modules
Because installed module packages load automatically, MVT records where every
module came from:
- `--list-modules` groups the available modules by source: MVT itself
(with its version), each installed package (with its version and, when
installed directly from a repository, the commit), and each file loaded
with `--load-module` or `MVT_CUSTOM_MODULES` (with the SHA-256 hash of the
file).
- When a command runs with an `--output` folder, the `command.log` file
records one line per module source with the source's version or hash and
the list of modules loaded from it.
- `mvt plugins list` lists the installed packages, where each of them
was installed from and how many modules it contributes, see
[Managing Plugins](plugins.md).
## Profiling
Some MVT modules extract and process significant amounts of data during the analysis process or while checking results against known indicators. Care must be
take to avoid inefficient code paths as we add new modules.
MVT modules can be profiled with Python built-in `cProfile` by setting the `MVT_PROFILE` environment variable.
```bash
MVT_PROFILE=1 dev/mvt-ios check-backup test_backup
```
Open an issue or PR if you are encountering significant performance issues when analyzing a device with MVT.
-157
View File
@@ -1,157 +0,0 @@
# Plugin Configuration
Plugin packages that add [custom CLI commands](custom_commands.md) or
[modules](index.md#installed-module-packages) often need to store their
own settings, such as an API key, a server URL or the timestamp of the last
synchronization. MVT provides a namespaced settings base class so each plugin
keeps its configuration in its own file, and a data folder for anything else a
plugin needs to keep on disk.
!!! warning
Do not write plugin settings to MVT's own `config.yaml`. MVT rewrites that
file with the settings it knows about every time it starts, so any other
section is deleted.
## Where Settings Are Stored
Each plugin gets one YAML file in a `plugins` folder next to MVT's own
configuration:
```
~/.config/mvt/plugins/<plugin name>.yaml
```
The exact parent folder follows the platform convention used for MVT's
`config.yaml` (for example `~/Library/Application Support/mvt` on macOS). Use
`plugin_config_path()` from `mvt.plugin` instead of building the path by hand.
Plugin names must be lowercase and may only contain letters, digits and dashes,
matching the `mvt-plugin-<name>` package naming convention. MVT creates the
`plugins` folder with `0700` permissions and writes the settings files with
`0600` permissions, because they commonly hold credentials. Files are written
through a temporary file and moved into place, so an interrupted save never
leaves a partially written settings file behind.
## Plugin Data Folder
Everything else a plugin keeps on disk, such as a cache, a downloaded artifact
or synchronization state, belongs in the folder returned by the `data_folder()`
class method of the plugin's settings class, or by `plugin_data_folder()` from
`mvt.plugin`, called with the plugin name if the plugin has no settings class:
```
~/.local/share/mvt/plugin-data/<plugin name>/ # Linux
~/Library/Application Support/mvt/plugin-data/<plugin name>/ # macOS
```
The folder sits beside MVT's own data, such as the downloaded indicators. It is
created if it is missing, with `0700` permissions. Asking for it again returns
the same path and leaves the contents alone, so a plugin can ask for it every
time it needs the folder. `ExamplePluginSettings` below is the settings class
defined in the next section:
```python
import os
def cache_path() -> str:
folder = ExamplePluginSettings.data_folder()
return os.path.join(folder, "virustotal_lookups_cache.json")
```
A plugin which has no settings class calls
`plugin_data_folder("example-plugin")` instead.
Do not fall back on a path of your own such as `~/.cache/example-plugin`: it
is a Linux-only convention, and MVT will not create it for you.
## Defining Plugin Settings
Subclass `MVTPluginSettings`, set `plugin_name` and declare typed fields with
defaults:
```python
from typing import Optional
from mvt.plugin import MVTPluginSettings
class ExamplePluginSettings(MVTPluginSettings):
plugin_name = "example-plugin"
API_KEY: Optional[str] = None
MAX_RESULTS: int = 25
LAST_SYNC: Optional[str] = None
```
`load()` returns the current settings and `save()` writes them back:
```python
from datetime import datetime, timezone
import click
from mvt.plugin import plugin_env_prefix
def sync():
settings = ExamplePluginSettings.load()
if not settings.API_KEY:
prefix = plugin_env_prefix(settings.plugin_name)
raise click.ClickException(
f"No API key configured. Set {prefix}API_KEY or "
"run 'example-plugin configure'."
)
settings.LAST_SYNC = datetime.now(timezone.utc).isoformat()
settings.save()
```
The message builds the variable name with `plugin_env_prefix()`, see
[Environment Variables](#environment-variables).
A missing settings file is not an error: the plugin then runs on the field
defaults and on whatever the environment provides. `save()` only persists the
values that differ from the defaults, and it never touches MVT's `config.yaml`.
A settings file that cannot be parsed, or that does not hold a mapping of
setting names to values, raises a `PluginConfigLoadError` naming the file.
Every subclass that sets its own `plugin_name` gets its own file and its own
environment namespace. A subclass that does not redefine `plugin_name` inherits
it, and therefore shares the file and the environment variables of its parent
class.
## Environment Variables
Every field can also be set with an environment variable. The prefix is
`MVT_PLUGIN_`, followed by the plugin name upper-cased with dashes replaced by
underscores, followed by the field name. For the example above:
```bash
export MVT_PLUGIN_EXAMPLE_PLUGIN_API_KEY=...
export MVT_PLUGIN_EXAMPLE_PLUGIN_MAX_RESULTS=50
```
Do not repeat the plugin name in a field name: a plugin named `example-scanner`
with a `SCANNER_API_KEY` field asks the user for
`MVT_PLUGIN_EXAMPLE_SCANNER_SCANNER_API_KEY`. Name the field `API_KEY`.
Settings resolve in this order, from highest to lowest priority:
1. Arguments passed to the settings class directly, such as
`ExamplePluginSettings(API_KEY="...")`
2. Environment variables
3. The plugin's YAML file
4. The field defaults declared on the settings class
!!! tip
On shared or multi-user machines, prefer passing API keys through
environment variables rather than saving them to the plugin file. `save()`
skips every value that the environment currently supplies, so a credential
provided that way is not copied into the settings file when a plugin saves
an unrelated setting.
Unknown keys in a plugin's YAML file are ignored, so a settings file written by
a newer version of a plugin does not break an older one.
-116
View File
@@ -1,116 +0,0 @@
# Managing Plugins
Plugin packages extend MVT with additional
[forensic modules](index.md#custom-modules) and
[CLI commands](custom_commands.md). Because installed packages load
automatically, `mvt plugins` audits what is installed and checks whether
updates are available. The command lives on `mvt` only, although the packages
it lists extend `mvt-ios` and `mvt-android` too.
## List Installed Plugins
```bash
mvt plugins list
```
```
Installed MVT plugins
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━┓
┃ Name ┃ Version ┃ Origin ┃ Modules ┃ Commands ┃
┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━┩
│ mvt-plugin-example │ 1.2.0 │ pypi │ 4 │ summarize │
│ mvt-plugin-research │ 0.1.0 │ git+3f9a1c7d │ 2 │ - │
│ mvt-plugin-local │ 0.0.1 │ local │ 1 │ triage │
└─────────────────────┴─────────┴──────────────┴─────────┴───────────┘
```
The origin records where each package was installed from: `pypi` for a package
installed from a package index, `git+<commit>` for a package installed directly
from a repository, and `local` for a package installed from a local folder or
archive rather than from an index, including an editable development install.
The last two columns show how many forensic modules the package contributes and
which CLI commands it adds.
A plugin whose modules cannot be imported is listed with `error` in the
`Modules` column rather than breaking the listing.
## Check for Updates
```bash
mvt plugins check-updates
```
```
Plugin updates available:
mvt-plugin-example 1.2.0 → 1.3.0
Upgrade with: pip install -U mvt-plugin-example
MVT does not install plugin updates. Run the command above when you decide to
upgrade.
```
Packages installed from a package index are compared against the latest release
published for them. A package which was never published, for example a plugin
distributed only within an organization, is skipped silently.
!!! note
Packages shown with the `pypi` origin are compared against
[PyPI](https://pypi.org), whichever index they were installed from. A
plugin installed from a private index under a name which also exists on
PyPI is therefore compared against the unrelated public package of that
name. Give plugins published to a private index a name which is not taken
on PyPI, and treat an unexpected update suggestion as a reason to check
where the package would come from.
!!! warning
MVT never installs or upgrades a plugin itself, it only prints the command
which does. Upgrading a plugin in the middle of an investigation changes
the modules producing the results, and a plugin runs as trusted code inside
the MVT process, so pulling in a new version is a decision for the analyst
to make deliberately and not a side effect of running a check.
## Automatic Update Checks
MVT also reports available plugin updates in the banner printed when a command
starts:
```
MVT - Mobile Verification Toolkit
https://mvt.re
Version: 2026.7.29
Plugin updates available:
mvt-plugin-example 1.2.0 → 1.3.0 (pip install -U mvt-plugin-example)
```
This check runs at most once every 12 hours. In between checks MVT prints the
findings of the latest check without contacting anything, so a plugin update
stays visible without a lookup on every command. The
`mvt plugins check-updates` command checks immediately, regardless of when the
last check happened.
The automatic check is skipped when the `--disable-update-check` option is
used, when `NETWORK_ACCESS_ALLOWED` is disabled in the MVT configuration, and
when no plugins are installed.
## Plugins Installed From a Repository
A plugin installed with `pip install "mvt-plugin-example @ git+<url>"` is
checked by asking the remote repository which commit the installed revision
points at now. MVT runs git and ssh in batch mode, so a repository which needs
credentials MVT does not already have fails the check instead of prompting for
them. The check is skipped silently when git is not available, when the
repository cannot be reached, and when access to it is denied.
How the plugin was installed decides what an update means:
- A plugin installed from a branch is reported as outdated when the branch has
moved past the installed commit.
- A plugin installed from a specific commit or a tag is pinned. It is never
reported as outdated, however far the branch it came from moves on.
Pinning a plugin to a commit or a tag is therefore the way to keep the modules
used across an investigation stable.
+1 -15
View File
@@ -31,18 +31,4 @@ Test if the image was created successfully:
docker run -it mvt
```
If a prompt is spawned successfully, you can close it with `exit`.
## Access an iOS device from Docker
On the Linux host, install and start [usbmuxd](https://github.com/libimobiledevice/usbmuxd), then connect and unlock the iOS device. The daemon exposes the device through the `/var/run/usbmuxd` socket.
Bind that socket into the container to let MVT communicate with the device:
```bash
docker run -it \
--mount type=bind,source=/var/run/usbmuxd,target=/var/run/usbmuxd \
ghcr.io/mvt-project/mvt
```
If you built the image from source, replace `ghcr.io/mvt-project/mvt` with `mvt`.
If a prompt is spawned successfully, you can close it with `exit`.
+1 -1
View File
@@ -9,7 +9,7 @@ Mobile Verification Toolkit (MVT) is a tool to facilitate the [consensual forens
It has been developed and released by the [Amnesty International Security Lab](https://securitylab.amnesty.org) in July 2021 in the context of the [Pegasus Project](https://forbiddenstories.org/about-the-pegasus-project/) along with [a technical forensic methodology](https://www.amnesty.org/en/latest/research/2021/07/forensic-methodology-report-how-to-catch-nso-groups-pegasus/). It continues to be maintained by Amnesty International and other contributors.
In this documentation you will find instructions on how to install and run the `mvt-ios`, `mvt-android` and `mvt` commands, and guidance on how to interpret the extracted results.
In this documentation you will find instructions on how to install and run the `mvt-ios` and `mvt-android` commands, and guidance on how to interpret the extracted results.
## Resources
+3 -3
View File
@@ -64,7 +64,7 @@ It is recommended to try installing and running MVT from [Windows Subsystem Linu
pipx install mvt
```
You now should have the `mvt`, `mvt-ios` and `mvt-android` utilities installed. If you run into problems with these commands not being found, ensure you have run `pipx ensurepath` and opened a new terminal window.
You now should have the `mvt-ios` and `mvt-android` utilities installed. If you run into problems with these commands not being found, ensure you have run `pipx ensurepath` and opened a new terminal window.
### Installing from PyPI directly into a virtual environment
You can use `pipenv`, `poetry` etc. for your virtual environment, but the provided example is with the built-in `venv` tool:
@@ -84,7 +84,7 @@ source env/bin/activate
pip install mvt
```
The `mvt`, `mvt-ios` and `mvt-android` utilities should now be available as commands whenever the virtual environment is active.
The `mvt-ios` and `mvt-android` utilities should now be available as commands whenever the virtual environment is active.
### Installing from git source with pipx
If you want to have the latest features in development, you can install MVT directly from the source code in git.
@@ -93,7 +93,7 @@ If you want to have the latest features in development, you can install MVT dire
pipx install --force git+https://github.com/mvt-project/mvt.git
```
You now should have the `mvt`, `mvt-ios` and `mvt-android` utilities installed.
You now should have the `mvt-ios` and `mvt-android` utilities installed.
**Notes:**
1. The `--force` flag is necessary to force the reinstallation of the package.
+1 -1
View File
@@ -71,7 +71,7 @@ So far MVT implements only a subset of [STIX2 specifications](https://docs.oasis
- [This repository](https://github.com/Te-k/stalkerware-indicators) contains IOCs for Android stalkerware including [a STIX MVT-compatible file](https://raw.githubusercontent.com/Te-k/stalkerware-indicators/master/generated/stalkerware.stix2).
- We are also maintaining [a list of IOCs](https://github.com/mvt-project/mvt-indicators) in STIX format from public spyware campaigns.
You can automatically download the latest public indicator files with the command `mvt download-iocs`. The per-platform forms `mvt-ios download-iocs` and `mvt-android download-iocs` do the same thing. These commands download the list of indicators from the [mvt-indicators](https://github.com/mvt-project/mvt-indicators/blob/main/indicators.yaml) repository and store them in the [appdir](https://pypi.org/project/appdirs/) folder. They are then loaded automatically by MVT.
You can automaticallly download the latest public indicator files with the command `mvt-ios download-iocs` or `mvt-android download-iocs`. These commands download the list of indicators from the [mvt-indicators](https://github.com/mvt-project/mvt-indicators/blob/main/indicators.yaml) repository and store them in the [appdir](https://pypi.org/project/appdirs/) folder. They are then loaded automatically by MVT.
Please [open an issue](https://github.com/mvt-project/mvt/issues/) to suggest new sources of STIX-formatted IOCs.
+1 -32
View File
@@ -312,15 +312,6 @@ If indicators are provided through the command-line, they are checked against th
---
### `urls.json`
This JSON file collects URLs extracted from SMS, iMessage, and WhatsApp
messages. Each entry contains the original URL, its expanded destination when
MVT resolved a shortened URL during indicator checking, the message timestamp,
and its `sms` or `whatsapp` source.
---
### `sms_attachments.json`
!!! info "Availability"
@@ -417,29 +408,7 @@ If indicators are provided through the command-line, they are checked against th
Backup: :material-check:
Full filesystem dump: :material-check:
This JSON file is created by mvt-ios' `WhatsApp` module. The module extracts a list of WhatsApp messages from the SQLite database located at *private/var/mobile/Containers/Shared/AppGroup/\*/ChatStorage.sqlite*, along with one record per chat session (marked with `"record_type": "chat_session"`) containing the first and last interaction dates of each conversation. Chat sessions produce `chat_first_message` and `chat_last_message` timeline events, and group chats additionally produce a `group_created` event. A chat session's last-message date can postdate its newest stored message when the most recent messages in the chat were deleted.
Recent WhatsApp versions key 1:1 chat sessions by an opaque LID identifier rather than the contact's phone number. The module resolves these using the `ZWAPHONENUMBERLIDPAIR` table from the *LID.sqlite* database in the same app group (or from *ChatStorage.sqlite* itself in versions that store it there), populating `partner_resolved_phone_number` on chat session records and using the phone number in timeline events. Each LID-phone number pair is also extracted as a record (`"record_type": "lid_phone_number_pair"`) and produces a `lid_pair_recorded` timeline event marking when WhatsApp learned the association.
This JSON file is created by mvt-ios' `WhatsApp` module. The module extracts a list of WhatsApp messages from the SQLite database located at *private/var/mobile/Containers/Shared/AppGroup/\*/ChatStorage.sqlite*.
If indicators are provided through the command-line, they are checked against the extracted HTTP links. Any matches are stored in *whatsapp_detected.json*.
---
### `whatsapp_contacts.json`
!!! info "Availability"
Backup: :material-check:
Full filesystem dump: :material-check:
This JSON file is created by mvt-ios' `WhatsappContacts` module. The module extracts WhatsApp contact records from the SQLite database located at *private/var/mobile/Containers/Shared/AppGroup/\*/ContactsV2.sqlite*, including each contact's phone number, WhatsApp and LID identifiers, and the per-contact disappearing messages timer, which is not recorded in *ChatStorage.sqlite*. Each timestamp stored on a contact record produces a timeline event: `disappearing_mode_set` (when the disappearing messages timer was last changed), `about_changed` (when the contact last changed their "about" text), `about_expiration` (when a timed "about" is scheduled to expire) and `contact_last_updated` (when the contact record was last updated).
This database is often missing from incremental backups. When it cannot be found, the module logs a warning and produces no results, in which case the disappearing messages state of chats cannot be determined from the backup.
---
## Records extracted by `check-sysdiagnose`
### `sysdiagnose_info.json`
This JSON file is created by mvt-ios' `SysdiagnoseInfo` module. The module extracts details about the device and the sysdiagnose itself: the product type and model, iOS version and build, serial number, IMEI, MEID and UDID from the remotectl dump state and the mobile activation request, the Apple account name and email from the App Store daemon database (no longer part of a sysdiagnose on newer iOS versions, still read from older archives), and the original file name and creation time of the archive from *sysdiagnose.log*.
+15 -22
View File
@@ -1,35 +1,30 @@
# Check an iOS Sysdiagnose
`mvt-ios check-sysdiagnose` analyzes an iOS sysdiagnose archive. MVT's own
`SysdiagnoseInfo` module extracts details about the device and the archive
(see [`sysdiagnose_info.json`](records.md#sysdiagnose_infojson)); the checks
come from the modules of the installed
[plugin packages](../development/index.md#installed-module-packages) which
declare support for the command. Without any such module the command still
records the device details, and warns that no forensic sysdiagnose modules
have been loaded so that the run cannot pass for a clean analysis.
`mvt-ios check-sysdiagnose` prepares an iOS sysdiagnose archive for analysis by
custom MVT modules. MVT does not include built-in sysdiagnose modules. You must
load at least one custom module that explicitly supports this command.
The command accepts either an extracted sysdiagnose directory or the original
gzip-compressed tar archive.
```bash
mvt-ios check-sysdiagnose --output ./results \
mvt-ios check-sysdiagnose \
--load-module ./sysdiagnose_modules.py \
--output ./results \
./sysdiagnose_2024.01.02_03-04-05+0200.tar.gz
```
Use `--hashes` to include hashes for analyzed files in `info.json`, and
`--list-modules` to display the eligible modules without running them.
`--list-modules` to display the eligible custom modules without running them.
## Writing a custom module
Extend `SysdiagnoseExtraction` from `mvt.plugin`, see
[Writing a module](../development/index.md#writing-a-module). The module reads
the archive the same way whether MVT was given a folder or a tar archive. It
declares the command in `supported_commands`. While writing one,
[load it from its file](../development/index.md#developing-modules-locally).
Extend `SysdiagnoseExtraction` to access the archive contents consistently for
both directory and tar inputs. Each module must declare the command explicitly
in `supported_commands`.
```python
from mvt.plugin import SysdiagnoseExtraction
from mvt.ios.modules.sysdiagnose import SysdiagnoseExtraction
class ExampleSysdiagnoseModule(SysdiagnoseExtraction):
@@ -49,9 +44,7 @@ class ExampleSysdiagnoseModule(SysdiagnoseExtraction):
return None
```
MVT extracts a tar archive first. It calls `from_sysdiagnose_folder()` on each
module before `run()`. `ips_files` lists the IPS crash reports.
`_get_files_by_pattern()` and `_get_file_content()` are internal helpers of the
base class. Use them to read the archive. Their names and signatures can change
between releases. See `src/mvt/ios/modules/sysdiagnose/base.py`.
The base class provides `from_sysdiagnose_folder()` and
`from_sysdiagnose_tar()` setup hooks, as well as protected file lookup, file
reading, and timezone extraction helpers. IPS crash-report metadata is exposed
on `ips_files`.
+1 -5
View File
@@ -49,9 +49,5 @@ nav:
- Check an Android Backup (SMS messages): "android/backup.md"
- Check Android Intrusion Logs: "android/intrusion_logs.md"
- Indicators of Compromise: "iocs.md"
- Development:
- Development Instructions: "development/index.md"
- Custom CLI Commands: "development/custom_commands.md"
- Plugin Configuration: "development/plugin_configuration.md"
- Managing Plugins: "development/plugins.md"
- Development: "development.md"
- License: "license.md"
+20 -21
View File
@@ -17,24 +17,25 @@ classifiers = [
"Programming Language :: Python",
]
dependencies = [
"click==8.4.2",
"rich==15.0.0",
"click==8.3.3",
"rich==14.3.3",
"tld==0.13.2",
"requests==2.34.2",
"simplejson==4.1.1",
"packaging==26.3",
"requests==2.33.1",
"simplejson==3.20.2",
"packaging==26.2",
"appdirs==1.4.4",
"iphone_backup_decrypt==0.10.0",
"pycryptodome>=3.20.0",
"cryptography==50.0.0",
"iOSbackup==0.9.925",
"adb-shell[usb]==0.4.4",
"libusb1==3.3.1",
"cryptography==47.0.0",
"PyYAML>=6.0.2",
"pyahocorasick==2.3.1",
"betterproto2==0.10.0",
"pydantic==2.13.4",
"pydantic-settings==2.15.0",
"betterproto2==0.9.1",
"pydantic==2.13.3",
"pydantic-settings==2.14.0",
"NSKeyedUnArchiver==1.5.2",
"python-dateutil==2.9.0.post0",
"tzdata==2026.3",
"tzdata==2026.2",
]
requires-python = ">= 3.10"
@@ -43,9 +44,8 @@ homepage = "https://docs.mvt.re/en/latest/"
repository = "https://github.com/mvt-project/mvt"
[project.scripts]
mvt = "mvt.cli:main"
mvt-ios = "mvt.ios:main"
mvt-android = "mvt.android:main"
mvt-ios = "mvt.ios:cli"
mvt-android = "mvt.android:cli"
[dependency-groups]
dev = [
@@ -65,13 +65,13 @@ dev = [
docs = [
"mkdocs==1.6.1",
"mkdocs-autorefs==1.4.4",
"mkdocs-material==9.7.7",
"mkdocs-material==9.7.6",
"mkdocs-material-extensions==1.3.1",
"mkdocstrings==1.0.6",
"mkdocstrings==1.0.4",
]
[build-system]
requires = ["setuptools>=61.0", "setuptools-scm>=8"]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[tool.coverage.run]
@@ -120,6 +120,5 @@ where = ["src"]
[tool.setuptools.package-data]
mvt = ["ios/data/*.json"]
[tool.setuptools_scm]
# The version is the latest v* tag; ignore the archive/* tags.
git_describe_command = "git describe --dirty --tags --long --match 'v*'"
[tool.setuptools.dynamic]
version = { attr = "mvt.common.version.MVT_VERSION" }
+1 -1
View File
@@ -3,4 +3,4 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from .cli import cli, main
from .cli import cli
@@ -4,51 +4,13 @@
# https://license.mvt.re/1.1/
import re
from typing import Any
from .artifact import AndroidArtifact
class DumpsysAccessibilityArtifact(AndroidArtifact):
# One list for both record shapes — a service record and a count-only
# record must stay the same shape.
_FIELDS = (
"user_id",
"component",
"package_name",
"service_name",
"installed",
"enabled",
"binding",
"bound",
"crashed",
"accessibility_tool",
"installed_service_count",
"unnamed_service_count",
)
def check_indicators(self) -> None:
for result in self.results:
# A stated count the dump does not back with component names is a
# coverage statement, not a service: low, but not silent.
if not result.get("component"):
stated = result["installed_service_count"]
unnamed = result["unnamed_service_count"]
if unnamed == stated:
detail = "does not list their component names"
else:
detail = (
f"lists the component names of only {stated - unnamed} "
f"of them ({unnamed} unnamed)"
)
self.alertstore.low(
f"The accessibility dump states {stated} installed "
f"service(s) for user {result['user_id']} but {detail}",
"",
result,
)
continue
if self.indicators:
ioc_match = self.indicators.check_app_id(result["package_name"])
if ioc_match:
@@ -57,22 +19,11 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
)
continue
# Installed is not enabled. A service can sit installed for years
# without ever being switched on, and that is the difference this
# channel is read for — an alert that says only "found" makes every
# device look equally exposed. A service the dump says is switched
# OFF is reported LOW, so it still reaches the analyst without
# competing with one that is actually running; a dump that does not
# state the enabled state stays MEDIUM, because "not stated" is not
# "not enabled".
message = (
f'Found accessibility service: "{result["component"]}" '
f"({self._describe_state(result)})"
)
if result.get("enabled") is False and not result.get("bound"):
self.alertstore.low(message, "", result)
else:
self.alertstore.medium(message, "", result)
self.alertstore.medium(
f'Found accessibility service: "{result["service"]}"',
"",
result,
)
def parse(self, content: str) -> None:
"""
@@ -82,122 +33,41 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
:param content: content of the accessibility section (string)
"""
self.results: list[dict[str, Any]] = []
services: dict[tuple[int | None, str], dict] = {}
# Which state sections the dump printed, per user: one user's printed
# `enabled services` says nothing about another user's.
seen_states: dict[int | None, set[str]] = {}
# `installedServiceCount=N` from the user's `attributes:{…}` line is on
# most builds the only statement about installed services in the dump:
# few print the `installed services: {…}` block.
installed_counts: dict[int | None, int] = {}
user_id: int | None = None
state: str | None = None
# "Old" syntax
in_services = False
for line in content.splitlines():
if line.strip().startswith("installed services:"):
in_services = True
continue
if not in_services:
continue
if line.strip() == "}":
# At end of installed services
break
service = line.split(":")[1].strip()
self.results.append(
{
"package_name": service.split("/")[0],
"service": service,
}
)
# "New" syntax - AOSP >= 14 (?)
# Looks like:
# Enabled services:{{com.azure.authenticator/com.microsoft.brooklyn.module.accessibility.BrooklynAccessibilityService}, {com.agilebits.onepassword/com.agilebits.onepassword.filling.accessibility.FillingAccessibilityService}}
for line in content.splitlines():
user_match = re.search(r"attributes:\{id=(\d+)", line)
if user_match:
user_id = int(user_match.group(1))
if line.strip().startswith("Enabled services:"):
matches = re.finditer(r"{([^{]+?)}", line)
count_match = re.search(r"installedServiceCount=(\d+)", line)
if count_match:
installed_counts[user_id] = int(count_match.group(1))
for match in matches:
# Each match is in format: <package_name>/<service>
package_name, _, service = match.group(1).partition("/")
stripped = line.strip()
state_match = re.match(
r"(?i)(installed|enabled|binding|bound|crashed) services\s*:\s*\{(.*)",
stripped,
)
if state_match:
state = state_match.group(1).lower()
seen_states.setdefault(user_id, set()).add(self._state_field(state))
inline = state_match.group(2)
for component in re.findall(
r"\{?([\w.$-]+/[\w.$-]+)(?:\s+\(A11yTool\))?\}?", inline
):
service = services.setdefault(
(user_id, component), self._new_service(component, user_id)
self.results.append(
{"package_name": package_name, "service": service}
)
service[self._state_field(state)] = True
service["accessibility_tool"] = "(A11yTool)" in inline
continue
if not state:
continue
if stripped == "}" or stripped.startswith("AccessibilityInputFilter"):
state = None
continue
component_match = re.search(
r"(?:\d+\s*:\s*)?([\w.$-]+/[\w.$-]+)(?:\s+\(A11yTool\))?",
stripped,
)
if component_match:
component = component_match.group(1)
service = services.setdefault(
(user_id, component), self._new_service(component, user_id)
)
service[self._state_field(state)] = True
service["accessibility_tool"] = "(A11yTool)" in stripped
# A section that was never printed is NOT the same as one printed
# empty: the first says nothing, the second says nothing is enabled.
# Defaulting every flag to False would turn "not stated" into "not
# enabled". Flags for sections this dump never printed stay None.
named: dict[int | None, int] = {}
for (service_user, _component), service in services.items():
printed = seen_states.get(service_user, set())
for state in ("installed", "enabled", "binding", "bound", "crashed"):
if self._state_field(state) not in printed:
service[self._state_field(state)] = None
service["installed_service_count"] = installed_counts.get(service_user)
named[service_user] = named.get(service_user, 0) + 1
self.results.extend(services.values())
# A stated count the named services do not add up to would leave no
# trace of the rest: the module would log "a total of 0" about a dump
# that said five, or "a total of 1" about one that said two.
for count_user, count in installed_counts.items():
unnamed = count - named.get(count_user, 0)
if unnamed > 0:
self.results.append(self._new_unlisted(count_user, count, unnamed))
@staticmethod
def _describe_state(result: dict) -> str:
if result.get("bound"):
return "enabled and bound"
if result.get("enabled"):
return "enabled"
if result.get("enabled") is None:
return "installed, enabled state not stated"
return "installed, not enabled"
@staticmethod
def _state_field(state: str) -> str:
return {"binding": "binding", "bound": "bound"}.get(state, state)
@staticmethod
def _new_unlisted(user_id: int | None, count: int, unnamed: int) -> dict:
"""The dump's own count for a user, and how many of those services it
did not name.
Every other field stays unknown: the dump named no service to carry it.
"""
record: dict[str, Any] = dict.fromkeys(DumpsysAccessibilityArtifact._FIELDS)
record["user_id"] = user_id
record["installed_service_count"] = count
record["unnamed_service_count"] = unnamed
return record
@staticmethod
def _new_service(component: str, user_id: int | None) -> dict:
record: dict[str, Any] = dict.fromkeys(
DumpsysAccessibilityArtifact._FIELDS, False
)
record["user_id"] = user_id
record["component"] = component
record["package_name"], record["service_name"] = component.split("/", 1)
# Filled in after parsing: the count is per user.
record["installed_service_count"] = None
record["unnamed_service_count"] = None
return record
+6 -86
View File
@@ -6,7 +6,6 @@
import base64
import binascii
import hashlib
import re
from .artifact import AndroidArtifact
@@ -29,21 +28,11 @@ class DumpsysADBArtifact(AndroidArtifact):
stack = [res]
cur_indent = 0
in_multiline = False
for line in dump_data.strip(b"\r\n").split(b"\n"):
line = line.removesuffix(b"\r")
for line in dump_data.strip(b"\n").split(b"\n"):
# Track the level of indentation
indent = len(line) - len(line.lstrip())
if indent < cur_indent:
# If the current line is less indented than the previous one, back out
if len(stack) <= 1:
# Dedenting below the outermost level means this is not the
# well-formed block the parser expects. Stop here rather than
# raise IndexError out of the module on the next line.
self.log.error(
"Unexpected indentation in ADB manager state, "
"stopping the parse of this section"
)
break
stack.pop()
cur_indent = indent
else:
@@ -73,12 +62,6 @@ class DumpsysADBArtifact(AndroidArtifact):
current_dict = stack[-1]
if key == "}":
if len(stack) <= 1:
self.log.error(
"Unbalanced closing brace in ADB manager state, "
"stopping the parse of this section"
)
break
stack.pop()
continue
@@ -115,34 +98,6 @@ class DumpsysADBArtifact(AndroidArtifact):
return keystore
def parse_binary_xml(self, data: bytes) -> list[dict]:
"""Recover ADB key records from Android binary XML (ABX).
Some dumpstate implementations embed ABX in a text stream and replace
binary token bytes. The public key remains intact, while unavailable
numeric metadata is represented as ``None`` rather than corrupt text.
"""
keystore = []
seen = set()
for match in re.finditer(
rb"(?<![A-Za-z0-9+/])([A-Za-z0-9+/]{300,}={0,2})"
rb"(?: ([A-Za-z0-9_.@-]+))?",
data,
):
key = match.group(1)
try:
base64.b64decode(key, validate=True)
except (binascii.Error, ValueError):
continue
if key in seen:
continue
seen.add(key)
full_key = key + (b" " + match.group(2) if match.group(2) else b"")
key_info = self.calculate_key_info(full_key)
key_info["last_connected"] = None
keystore.append(key_info)
return keystore
@staticmethod
def calculate_key_info(user_key: bytes) -> dict:
if b" " in user_key:
@@ -163,7 +118,7 @@ class DumpsysADBArtifact(AndroidArtifact):
return {
"user": user.decode("utf-8"),
"fingerprint": key_fingerprint_colon,
"key": key_base64.decode("ascii", errors="replace"),
"key": key_base64,
}
def check_indicators(self) -> None:
@@ -177,26 +132,6 @@ class DumpsysADBArtifact(AndroidArtifact):
f"'{user_key['fingerprint']}'"
)
@staticmethod
def _find_state_end(content: bytes, open_brace: int) -> int:
"""Find the unindented line closing the ADB manager state, or -1.
Braces inside key comments or embedded keystore data are values, while
nested structural closing braces are indented.
"""
line_start = open_brace
while line_start < len(content):
line_end = content.find(b"\n", line_start)
if line_end == -1:
line_end = len(content)
line = content[line_start:line_end].removesuffix(b"\r")
if line_start > open_brace and line == b"}":
return line_start
if line.startswith((b"---------", b"DUMP OF SERVICE ")):
break
line_start = line_end + 1
return -1
def parse(self, content: bytes) -> None:
"""
Parse the Dumpsys ADB section
@@ -216,16 +151,12 @@ class DumpsysADBArtifact(AndroidArtifact):
self.log.error("Unable to find ADB manager state in dumpsys output")
return
end_of_json = self._find_state_end(content, start_of_json + 1)
if end_of_json == -1:
self.log.error(
"Unable to find complete ADB manager state in dumpsys output"
)
end_of_json = content.rfind(b"}\n")
if end_of_json == -1 or end_of_json <= start_of_json:
self.log.error("Unable to find complete ADB manager state in dumpsys output")
return
# The brace that opens the state and the one that closes it are not part
# of the indented body.
json_content = content[start_of_json + 2 : end_of_json].rstrip()
json_content = content[start_of_json + 2 : end_of_json - 2].rstrip()
parsed = self.indented_dump_parser(json_content)
if parsed.get("debugging_manager") is None:
@@ -244,23 +175,12 @@ class DumpsysADBArtifact(AndroidArtifact):
# Keystore is in XML format on some devices and we need to parse it
if keystore_data and keystore_data.startswith(b"<?xml"):
parsed["debugging_manager"]["keystore"] = self.parse_xml(keystore_data)
elif keystore_data and keystore_data.startswith(b"ABX\x00"):
parsed["debugging_manager"]["keystore"] = self.parse_binary_xml(
keystore_data
)
else:
# Keystore is not XML format
parsed["debugging_manager"]["keystore"] = keystore_data
parsed = parsed["debugging_manager"]
for key, value in list(parsed.items()):
if isinstance(value, bytes):
decoded = value.decode("utf-8", errors="replace")
parsed[key] = (
decoded == "true" if decoded in ("true", "false") else decoded
)
# Calculate key fingerprints for better readability
key_info = []
for user_key in parsed.get("user_keys", []):
+81 -122
View File
@@ -4,7 +4,6 @@
# https://license.mvt.re/1.1/
from datetime import datetime
import re
from typing import Any
from mvt.common.module_types import ModuleAtomicResult, ModuleSerializedResult
@@ -28,14 +27,14 @@ class DumpsysAppopsArtifact(AndroidArtifact):
continue
for entry in perm["entries"]:
if entry.get("timestamp"):
if "timestamp" in entry:
records.append(
{
"timestamp": entry["timestamp"],
"module": self.__class__.__name__,
"event": entry["event"],
"event": entry["access"],
"data": f"{result['package_name']} access to "
f"{perm['name']}: {entry['event']}",
f"{perm['name']}: {entry['access']}",
}
)
@@ -52,7 +51,7 @@ class DumpsysAppopsArtifact(AndroidArtifact):
continue
# We use a placeholder entry to create a basic alert even without permission entries.
placeholder_entry = {"event": "unknown", "timestamp": ""}
placeholder_entry = {"access": "Unknown", "timestamp": ""}
for perm in result["permissions"]:
if (
@@ -61,12 +60,12 @@ class DumpsysAppopsArtifact(AndroidArtifact):
):
for entry in sorted(
perm["entries"] or [placeholder_entry],
key=lambda x: x.get("timestamp") or "",
key=lambda x: x["timestamp"],
):
cleaned_result = result.copy()
cleaned_result["permissions"] = [perm]
self.alertstore.medium(
f"Package '{result['package_name']}' had risky permission '{perm['name']}' set to '{entry['event']}' at {entry['timestamp']}",
f"Package '{result['package_name']}' had risky permission '{perm['name']}' set to '{entry['access']}' at {entry['timestamp']}",
entry["timestamp"],
cleaned_result,
)
@@ -74,151 +73,111 @@ class DumpsysAppopsArtifact(AndroidArtifact):
elif result["package_name"] in RISKY_PACKAGES:
for entry in sorted(
perm["entries"] or [placeholder_entry],
key=lambda x: x.get("timestamp") or "",
key=lambda x: x["timestamp"],
):
cleaned_result = result.copy()
cleaned_result["permissions"] = [perm]
self.alertstore.medium(
f"Risky package '{result['package_name']}' had '{perm['name']}' permission set to '{entry['event']}' at {entry['timestamp']}",
f"Risky package '{result['package_name']}' had '{perm['name']}' permission set to '{entry['access']}' at {entry['timestamp']}",
entry["timestamp"],
cleaned_result,
)
def parse(self, output: str) -> None:
self.results: list[dict[str, Any]] = []
permission: dict[str, Any] | None = None
package: dict[str, Any] | None = None
uid: str | None = None
uid_details: dict[str, Any] = {}
attribution: str | None = None
# self.results: List[Dict[str, Any]] = []
perm: dict[str, Any] = {}
package: dict[str, Any] = {}
entry: dict[str, Any] = {}
uid = None
in_packages = False
def finish_permission() -> None:
nonlocal permission
if package is not None and permission is not None:
package["permissions"].append(permission)
permission = None
def finish_package() -> None:
nonlocal package
finish_permission()
if package is not None:
self.results.append(package)
package = None
for line in output.splitlines():
uid_match = re.match(r"^ Uid ([^:]+):$", line)
if uid_match:
if line.startswith(" Uid 0:"):
in_packages = True
finish_package()
uid = uid_match.group(1)
uid_details = {
"uid_state": None,
"capability": None,
"app_widget_visible": None,
"default_modes": {},
}
continue
if not in_packages:
continue
uid_property = re.match(
r"^ (state|capability|appWidgetVisible)=(.*)$", line
)
if uid_property:
key = {
"state": "uid_state",
"appWidgetVisible": "app_widget_visible",
}.get(uid_property.group(1), uid_property.group(1))
value: Any = uid_property.group(2)
if value in ("true", "false"):
value = value == "true"
uid_details[key] = value
continue
if line.startswith(" Uid "):
uid = line[6:-1]
if entry:
perm["entries"].append(entry)
entry = {}
if package:
if perm:
package["permissions"].append(perm)
default_mode = re.match(r"^ ([A-Z0-9_]+): mode=([^\s]+)", line)
if default_mode and package is None:
uid_details["default_modes"][default_mode.group(1)] = (
default_mode.group(2)
)
perm = {}
self.results.append(package)
package = {}
continue
if line.startswith(" Package "):
finish_package()
if entry:
perm["entries"].append(entry)
entry = {}
if package:
if perm:
package["permissions"].append(perm)
perm = {}
self.results.append(package)
package = {
"package_name": line[12:-1],
"permissions": [],
"uid": uid,
**uid_details,
}
continue
operation_match = re.match(
r"^ ([A-Z0-9_]+)(?: \(([^)]+)\))?:\s*$", line
)
if package is not None and operation_match:
finish_permission()
permission = {
"name": operation_match.group(1),
"mode": operation_match.group(2),
"entries": [],
}
attribution = None
if package and line.startswith(" ") and line[6] != " ":
if entry:
perm["entries"].append(entry)
entry = {}
if perm:
package["permissions"].append(perm)
perm = {}
perm["name"] = line.split()[0]
perm["entries"] = []
if len(line.split()) > 1:
perm["access"] = line.split()[1][1:-2]
continue
attribution_match = re.match(r"^\s{8,}([^=]+)=\[$", line)
if attribution_match:
attribution = attribution_match.group(1).strip()
continue
if line.strip() == "]":
attribution = None
continue
if line.startswith(" "):
# Permission entry like:
# Reject: [fg-s]2021-05-19 22:02:52.054 (-314d1h25m2s33ms)
access_type = line.split(":")[0].strip()
if access_type not in ["Access", "Reject"]:
# Skipping invalid access type. Some entries are not in the format we expect
continue
if permission is None:
continue
event_match = re.match(
r"^\s*(Access|Reject):\s*\[([^]]+)\]\s*"
r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d+)\s*"
r"(\([^)]*\))?(?:\s+duration=([^\s]+))?",
line,
)
running_match = re.match(
r"^\s*Running start at:\s*(\S+(?: \S+)?)",
line,
)
if event_match:
entry = {
"event": event_match.group(1).lower(),
"access": event_match.group(1),
"uid_state": event_match.group(2),
"timestamp": convert_datetime_to_iso(
datetime.strptime(event_match.group(3), "%Y-%m-%d %H:%M:%S.%f")
),
"relative_time": event_match.group(4),
"duration": event_match.group(5),
"attribution": attribution,
}
permission["entries"].append(entry)
elif running_match:
raw_start = running_match.group(1)
timestamp = None
if re.fullmatch(r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d+", raw_start):
timestamp = convert_datetime_to_iso(
datetime.strptime(raw_start, "%Y-%m-%d %H:%M:%S.%f")
if entry:
perm["entries"].append(entry)
entry = {}
entry["access"] = access_type
entry["type"] = line[line.find("[") + 1 : line.find("]")]
try:
entry["timestamp"] = convert_datetime_to_iso(
datetime.strptime(
line[line.find("]") + 1 : line.find("(")].strip(),
"%Y-%m-%d %H:%M:%S.%f",
)
)
permission["entries"].append(
{
"event": "running",
"access": "Running",
"uid_state": None,
"timestamp": timestamp,
"relative_time": raw_start
if raw_start.startswith("+")
else None,
"duration": None,
"attribution": attribution,
}
)
except ValueError:
# Invalid date format
pass
finish_package()
if line.strip() == "":
break
if entry:
perm["entries"].append(entry)
if perm:
package["permissions"].append(perm)
if package:
self.results.append(package)
@@ -18,18 +18,18 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
def serialize(self, record: ModuleAtomicResult) -> ModuleSerializedResult:
action = record.get("action", "update")
package_name = record["package_name"]
vers = record["version_code"]
vers = record["vers"]
if vers == 0:
if vers == "0":
data = f"Recorded uninstall of package {package_name} (vers 0)"
elif action == "downgrade":
prev_vers = record.get("previous_version_code", "unknown")
prev_vers = record.get("previous_vers", "unknown")
data = f"Recorded downgrade of package {package_name} from vers {prev_vers} to vers {vers}"
else:
data = f"Recorded update of package {package_name} with vers {vers}"
return {
"timestamp": record["period_start"],
"timestamp": record["from"],
"module": self.__class__.__name__,
"event": "battery_daily",
"data": data,
@@ -48,7 +48,6 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
continue
def parse(self, output: str) -> None:
self.results = []
daily = None
daily_updates: list[dict[str, Any]] = []
records: list[dict[str, Any]] = []
@@ -60,10 +59,7 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
timeframe = line[13:].strip()
date_from, date_to = timeframe.strip(":").split(" to ", 1)
daily = {
"period_start": self._format_daily_timestamp(date_from),
"period_end": self._format_daily_timestamp(date_to),
}
daily = {"from": date_from[0:10], "to": date_to[0:10]}
continue
if not daily:
@@ -73,35 +69,22 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
continue
line = line.strip().replace("Update ", "")
# A truncated or vendor-specific line must not abort the parse and
# lose every record after it.
package_name, _, vers = line.partition(" ")
vers_raw = vers.partition("=")[2]
if not package_name or not vers_raw:
continue
try:
version_code: int | str = int(vers_raw)
except ValueError:
version_code = vers_raw
package_name, vers = line.split(" ", 1)
vers_nr = vers.split("=", 1)[1]
already_seen = False
for update in daily_updates:
if (
package_name == update["package_name"]
and version_code == update["version_code"]
):
update["occurrences"] += 1
if package_name == update["package_name"] and vers_nr == update["vers"]:
already_seen = True
break
if not already_seen:
update_record: dict[str, Any] = {
"action": "update",
"period_start": daily["period_start"],
"period_end": daily["period_end"],
"from": daily["from"],
"to": daily["to"],
"package_name": package_name,
"version_code": version_code,
"occurrences": 1,
"vers": vers_nr,
}
daily_updates.append(update_record)
@@ -112,31 +95,26 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
self._detect_uninstalls_and_downgrades(records)
self.results.extend(records)
@staticmethod
def _format_daily_timestamp(value: str) -> str:
if len(value) >= 19 and value[10] == "-":
return f"{value[:10]} {value[11:].replace('-', ':')}"
return value
def _detect_uninstalls_and_downgrades(self, records: list[dict[str, Any]]) -> None:
def _detect_uninstalls_and_downgrades(
self, records: list[dict[str, Any]]
) -> None:
package_versions: dict[str, int] = {}
for record in sorted(
records,
key=lambda record: (
record["period_start"],
record["period_end"],
record["from"],
record["to"],
record["package_name"],
),
):
package_name = record["package_name"]
vers_nr = record["version_code"]
vers_nr = record["vers"]
if vers_nr == 0:
record["action"] = "uninstall"
if vers_nr == "0":
self.alertstore.medium(
f"Detected uninstall of package {package_name} (vers 0)",
record["period_start"],
record["from"],
record,
)
package_versions.pop(package_name, None)
@@ -150,11 +128,11 @@ class DumpsysBatteryDailyArtifact(AndroidArtifact):
previous_vers = package_versions.get(package_name)
if previous_vers is not None and current_vers < previous_vers:
record["action"] = "downgrade"
record["previous_version_code"] = previous_vers
record["previous_vers"] = str(previous_vers)
self.alertstore.medium(
f"Detected downgrade of package {package_name} "
f"from vers {previous_vers} to vers {current_vers}",
record["period_start"],
record["from"],
record,
)
@@ -1,177 +1,96 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Copyright (c) 2021-2023 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import datetime
import re
from mvt.common.utils import convert_datetime_to_iso
from .artifact import AndroidArtifact
class DumpsysBatteryHistoryArtifact(AndroidArtifact):
"""Parser for package-related events in dumpsys batterystats history."""
"""
Parser for dumpsys dattery history events.
"""
def check_indicators(self) -> None:
if not self.indicators:
return
for result in self.results:
package_name = result.get("package_name")
if not package_name:
continue
ioc_match = self.indicators.check_app_id(package_name)
ioc_match = self.indicators.check_app_id(result["package_name"])
if ioc_match:
self.alertstore.critical(
ioc_match.message, "", result, matched_indicator=ioc_match.ioc
)
@staticmethod
def _parse_wall_time(value: str) -> datetime.datetime | None:
if re.fullmatch(r"\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d+", value):
value = f"1900-{value}"
for date_format in (
"%Y-%m-%d-%H-%M-%S-%f",
"%Y-%m-%d-%H-%M-%S",
"%Y-%m-%d %H:%M:%S.%f",
):
try:
return datetime.datetime.strptime(value, date_format)
except ValueError:
pass
return None
@staticmethod
def _elapsed_seconds(value: str) -> float | None:
if not value.startswith("+"):
return None
units = {"d": 86400, "h": 3600, "m": 60, "s": 1, "ms": 0.001}
total = 0.0
for number, unit in re.findall(r"(\d+)(ms|d|h|m|s)", value):
total += int(number) * units[unit]
return total
@staticmethod
def _package_from_name(name: str) -> str | None:
clean = name.removeprefix("*walarm*:").removeprefix("*alarm*:")
slash_parts = clean.split("/")
if len(slash_parts) > 1:
first = slash_parts[0].lstrip("@")
if first.startswith(("com.", "org.", "net.")):
return first
for part in reversed(slash_parts[1:]):
candidate = part.lstrip("@").split(":", 1)[0]
if candidate.startswith(("com.", "org.", "net.")):
return candidate
parts = clean.split(".")
package_parts = []
for part in parts:
if part and part[0].islower():
package_parts.append(part)
else:
break
return ".".join(package_parts) if len(package_parts) >= 2 else None
@staticmethod
def _normalize_service(service: str) -> str:
# WorkManager decorates jobs with one or more scheduler prefixes.
if "@" in service:
candidates = [part for part in service.split("@") if "/" in part]
if candidates:
return candidates[-1]
return service
continue
def parse(self, data: str) -> None:
self.results: list[dict[str, str | None]] = []
anchor_time: datetime.datetime | None = None
anchor_elapsed = 0.0
has_history_heading = any(
line.startswith("Battery History") for line in data.splitlines()
)
in_history = not has_history_heading
for line in data.splitlines():
stripped = line.strip()
if line.startswith("Battery History"):
if in_history:
break
in_history = True
if line.startswith("Battery History "):
continue
if not in_history:
continue
if has_history_heading and not stripped:
if line.strip() == "":
break
reset_match = re.search(r"(?:RESET:)?TIME:\s*(\S+)", stripped)
if reset_match:
parsed_time = self._parse_wall_time(reset_match.group(1))
if parsed_time is not None:
elapsed_token = stripped.split()[0]
anchor_elapsed = self._elapsed_seconds(elapsed_token) or 0.0
anchor_time = parsed_time
continue
fields = stripped.split()
if not fields:
continue
if len(fields) > 1 and re.fullmatch(r"\d{2}-\d{2}", fields[0]):
time_elapsed = " ".join(fields[:2])
line_time = self._parse_wall_time(time_elapsed)
elapsed = None
time_parts = line.strip().split()
time_elapsed = time_parts[0]
if (
len(time_parts) > 1
and len(time_parts[0]) == 5
and time_parts[0][2] == "-"
and ":" in time_parts[1]
):
time_elapsed = " ".join(time_parts[:2])
event = ""
if line.find("+job") > 0:
event = "start_job"
payload = line.split("+job=", 1)[1]
uid, separator, service = payload.partition(":")
if not separator:
continue
service = service.strip().strip('"')
package_name = service.split("/")[0]
elif line.find("-job") > 0:
event = "end_job"
payload = line.split("-job=", 1)[1]
uid, separator, service = payload.partition(":")
if not separator:
continue
service = service.strip().strip('"')
package_name = service.split("/")[0]
elif line.find("+running +wake_lock=") > 0:
payload = line.split("+running +wake_lock=", 1)[1]
uid, separator, _ = payload.partition(":")
if not separator:
continue
event = "wake"
service = (
line[line.find("*walarm*:") + 9 :].split(" ")[0].strip('"').strip()
)
if service == "" or "/" not in service:
continue
package_name = service.split("/")[0]
elif (line.find("+top=") > 0) or (line.find("-top") > 0):
if line.find("+top=") > 0:
event = "start_top"
top_pos = line.find("+top=")
else:
event = "end_top"
top_pos = line.find("-top=")
colon_pos = top_pos + line[top_pos:].find(":")
uid = line[top_pos + 5 : colon_pos]
service = ""
package_name = line[colon_pos + 1 :].strip('"')
else:
time_elapsed = fields[0]
elapsed = self._elapsed_seconds(time_elapsed)
line_time = None
continue
timestamp = line_time
if timestamp is None and anchor_time is not None and elapsed is not None:
timestamp = anchor_time + datetime.timedelta(
seconds=elapsed - anchor_elapsed
)
def add(
event: str, uid: str, service: str, package_name: str | None
) -> None:
self.results.append(
{
"time_elapsed": time_elapsed,
"timestamp": convert_datetime_to_iso(timestamp)
if timestamp
else None,
"event": event,
"uid": uid,
"package_name": package_name,
"service": service,
}
)
for sign, uid, raw_service in re.findall(
r"([+-])job=([^:\s]+):\"([^\"]+)\"", line
):
service = self._normalize_service(raw_service)
add(
"start_job" if sign == "+" else "end_job",
uid,
service,
self._package_from_name(service) or service.split("/", 1)[0],
)
for sign, uid, package_name in re.findall(
r"([+-])top=([^:\s]+):\"([^\"]+)\"", line
):
add(
"start_top" if sign == "+" else "end_top",
uid,
"",
package_name,
)
wake_match = re.search(r"\+wake_lock=([^:\s]+):\"([^\"]+)\"", line)
if wake_match:
wake_name = wake_match.group(2)
add(
"wake",
wake_match.group(1),
wake_name,
self._package_from_name(wake_name),
)
self.results.append(
{
"time_elapsed": time_elapsed,
"event": event,
"uid": uid,
"package_name": package_name,
"service": service,
}
)
+11 -25
View File
@@ -29,27 +29,16 @@ class DumpsysDBInfoArtifact(AndroidArtifact):
def parse(self, output: str) -> None:
rxp = re.compile(
r"^\s*\d+:\s*\[((?:\d{4}-)?\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d{3})\]\s*"
r"(?:\[Pid:\((\d+)\)\])?\s*([\w-]+) took (\d+)ms - ([^,]+),"
r"\s*sql=\"(.*)\"(?:, path=(.*))?$"
)
r".*\[((?:[0-9]{4}-)?[0-9]{2}-[0-9]{2} "
r"[0-9]{2}:[0-9]{2}:[0-9]{2}\.[0-9]{3})\]\s*"
r"(?:\[Pid:\((\d+)\)\])?([\w-]+).*?sql=\"(.+?)\""
) # pylint: disable=line-too-long
pool: str | None = None
connection_number: int | None = None
is_primary: bool | None = None
pool = None
in_operations = False
for line in output.splitlines():
if line.startswith("Connection pool for "):
pool = line.replace("Connection pool for ", "").rstrip(":")
in_operations = False
connection_match = re.match(r"\s+Connection #(\d+):", line)
if connection_match:
connection_number = int(connection_match.group(1))
is_primary = None
if line.strip().startswith("isPrimaryConnection:"):
is_primary = line.strip().split(":", 1)[1].strip() == "true"
if not pool:
continue
@@ -63,6 +52,7 @@ class DumpsysDBInfoArtifact(AndroidArtifact):
if not line.startswith(" "):
in_operations = False
pool = None
continue
match = rxp.match(line)
@@ -70,15 +60,11 @@ class DumpsysDBInfoArtifact(AndroidArtifact):
continue
result = {
"timestamp": match.group(1),
"pid": int(match.group(2)) if match.group(2) else None,
"isodate": match.group(1),
"action": match.group(3),
"duration_ms": int(match.group(4)),
"status": match.group(5),
"sql": match.group(6),
"path": match.group(7) or pool,
"pool_path": pool,
"connection_number": connection_number,
"is_primary": is_primary,
"sql": match.group(4),
"path": pool,
}
if match.group(2):
result["pid"] = match.group(2)
self.results.append(result)
@@ -4,7 +4,6 @@
# https://license.mvt.re/1.1/
from .artifact import AndroidArtifact
from .package_resolvers import parse_resolver_table
class DumpsysPackageActivitiesArtifact(AndroidArtifact):
@@ -20,11 +19,67 @@ class DumpsysPackageActivitiesArtifact(AndroidArtifact):
)
continue
def parse(self, content: str) -> None:
def parse(self, content: str):
"""
Parse the Dumpsys Package section for activities
Adds results to self.results
:param content: content of the package section (string)
"""
self.results = parse_resolver_table(content, "Activity")
self.results = []
in_activity_resolver_table = False
in_non_data_actions = False
intent = None
for line in content.splitlines():
if line.startswith("Activity Resolver Table:"):
in_activity_resolver_table = True
continue
if not in_activity_resolver_table:
continue
if line.startswith(" Non-Data Actions:"):
in_non_data_actions = True
continue
if not in_non_data_actions:
continue
# If we hit an empty line, the Non-Data Actions section should be
# finished.
if line.strip() == "":
break
# We detect the action name.
if (
line.startswith(" " * 6)
and not line.startswith(" " * 8)
and ":" in line
):
intent = line.strip().replace(":", "")
continue
# If we are not in an intent block yet, skip.
if not intent:
continue
# If we are in a block but the line does not start with 8 spaces
# it means the block ended a new one started, so we reset and
# continue.
if not line.startswith(" " * 8):
intent = None
continue
# If we got this far, we are processing receivers for the
# activities we are interested in.
activity = line.strip().split(" ")[1]
package_name = activity.split("/")[0]
self.results.append(
{
"intent": intent,
"package_name": package_name,
"activity": activity,
}
)
+162 -210
View File
@@ -1,10 +1,10 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Copyright (c) 2021-2023 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import re
from typing import Any
from typing import Any, Dict, List
from mvt.android.utils import ROOT_PACKAGES
from mvt.common.module_types import ModuleAtomicResult, ModuleSerializedResult
@@ -12,244 +12,196 @@ from mvt.common.module_types import ModuleAtomicResult, ModuleSerializedResult
from .artifact import AndroidArtifact
def _value(raw: str) -> Any:
if raw == "null":
return None
if raw in ("true", "false"):
return raw == "true"
try:
return int(raw)
except ValueError:
return raw
class DumpsysPackagesArtifact(AndroidArtifact):
def check_indicators(self) -> None:
alerted_root_packages = set()
for result in self.results:
package_name = result["package_name"]
if (
package_name in ROOT_PACKAGES
and package_name not in alerted_root_packages
):
alerted_root_packages.add(package_name)
if result["package_name"] in ROOT_PACKAGES:
if result["package_name"] in alerted_root_packages:
continue
alerted_root_packages.add(result["package_name"])
self.alertstore.medium(
f'Found an installed package related to rooting/jailbreaking: "{package_name}"',
f'Found an installed package related to rooting/jailbreaking: "{result["package_name"]}"',
"",
result,
)
continue
if not self.indicators:
continue
ioc_match = self.indicators.check_app_id(package_name)
ioc_match = self.indicators.check_app_id(result.get("package_name", ""))
if ioc_match:
self.alertstore.critical(
ioc_match.message, "", result, matched_indicator=ioc_match.ioc
)
def serialize(self, record: ModuleAtomicResult) -> ModuleSerializedResult:
records = []
timestamps = [
("package_install", record.get("timestamp")),
("package_last_update", record.get("last_update_time")),
]
timestamps.extend(
("package_first_install", user.get("first_install_time"))
for user in record.get("users", [])
)
return [
{"event": "package_install", "timestamp": record["timestamp"]},
{
"timestamp": timestamp,
"module": self.__class__.__name__,
"event": event,
"data": f"Install or update of package {record['package_name']}",
}
for event, timestamp in timestamps
if timestamp
"event": "package_first_install",
"timestamp": record["first_install_time"],
},
{"event": "package_last_update", "timestamp": record["last_update_time"]},
]
for timestamp in timestamps:
records.append(
{
"timestamp": timestamp["timestamp"],
"module": self.__class__.__name__,
"event": timestamp["event"],
"data": f"Install or update of package {record['package_name']}",
}
)
return records
@staticmethod
def _permission(line: str, permission_type: str) -> dict:
name, _, details = line.strip().partition(":")
granted_match = re.search(r"granted=(true|false)", details)
flags_match = re.search(r"flags=\[\s*([^]]*)\]", details)
return {
"name": name,
"type": permission_type,
"granted": granted_match.group(1) == "true" if granted_match else None,
"flags": [
flag.strip()
for flag in (flags_match.group(1).split("|") if flags_match else [])
if flag.strip()
],
def parse_dumpsys_package_for_details(output: str) -> Dict[str, Any]:
"""
Parse one entry of a dumpsys package information
"""
details: Dict[str, Any] = {
"uid": "",
"version_name": "",
"version_code": "",
"timestamp": "",
"first_install_time": "",
"last_update_time": "",
"permissions": list(),
"requested_permissions": list(),
}
@classmethod
def parse_dumpsys_package_for_details(cls, output: str) -> dict[str, Any]:
details: dict[str, Any] = {
"app_id": None,
"version_name": None,
"version_code": None,
"min_sdk": None,
"target_sdk": None,
"timestamp": None,
"last_update_time": None,
"installer": None,
"system": False,
"permissions": [],
"requested_permissions": [],
"users": [],
}
permission_section: str | None = None
current_user: dict[str, Any] | None = None
legacy_first_install: str | None = None
in_install_permissions = False
in_runtime_permissions = False
in_declared_permissions = False
in_requested_permissions = True
for line in output.splitlines():
stripped = line.strip()
user_match = re.match(r"User (\d+):\s*(.*)", stripped)
if user_match:
current_user = {"user_id": int(user_match.group(1)), "permissions": []}
for key, raw in re.findall(r"(\w+)=([^\s]+)", user_match.group(2)):
clean_key = {
"notLaunched": "not_launched",
"installReason": "install_reason",
"uninstallReason": "uninstall_reason",
"dataDir": "data_dir",
}.get(key, re.sub(r"(?<!^)(?=[A-Z])", "_", key).lower())
current_user[clean_key] = _value(raw)
details["users"].append(current_user)
permission_section = None
continue
if in_install_permissions:
if line.startswith(" " * 4) and not line.startswith(" " * 6):
in_install_permissions = False
else:
lineinfo = line.strip().split(":")
permission = lineinfo[0]
granted = None
if "granted=" in lineinfo[1]:
granted = "granted=true" in lineinfo[1]
header = stripped.lower()
if header in {
"declared permissions:",
"install permissions:",
"requested permissions:",
"runtime permissions:",
}:
permission_section = header.split()[0]
continue
details["permissions"].append(
{"name": permission, "granted": granted, "type": "install"}
)
if in_runtime_permissions:
if not line.startswith(" " * 8):
in_runtime_permissions = False
else:
lineinfo = line.strip().split(":")
permission = lineinfo[0]
granted = None
if "granted=" in lineinfo[1]:
granted = "granted=true" in lineinfo[1]
if current_user is not None:
user_property = re.match(
r"(installReason|uninstallReason|dataDir|firstInstallTime)=(.*)",
stripped,
)
if user_property:
key = {
"installReason": "install_reason",
"uninstallReason": "uninstall_reason",
"dataDir": "data_dir",
"firstInstallTime": "first_install_time",
}[user_property.group(1)]
current_user[key] = _value(user_property.group(2))
continue
details["permissions"].append(
{"name": permission, "granted": granted, "type": "runtime"}
)
if in_declared_permissions:
if not line.startswith(" " * 6):
in_declared_permissions = False
else:
permission = line.strip().split(":")[0]
details["permissions"].append(
{"name": permission, "type": "declared"}
)
if in_requested_permissions:
if not line.startswith(" " * 6):
in_requested_permissions = False
else:
details["requested_permissions"].append(line.strip())
if line.strip().startswith("userId="):
details["uid"] = line.split("=")[1].strip()
elif line.strip().startswith("versionName="):
details["version_name"] = line.split("=")[1].strip()
elif line.strip().startswith("versionCode="):
details["version_code"] = line.split("=", 1)[1].strip()
elif line.strip().startswith("timeStamp="):
details["timestamp"] = line.split("=")[1].strip()
elif line.strip().startswith("firstInstallTime="):
details["first_install_time"] = line.split("=")[1].strip()
elif line.strip().startswith("lastUpdateTime="):
details["last_update_time"] = line.split("=")[1].strip()
elif line.strip() == "install permissions:":
in_install_permissions = True
elif line.strip() == "runtime permissions:":
in_runtime_permissions = True
elif line.strip() == "declared permissions:":
in_declared_permissions = True
elif line.strip() == "requested permissions:":
in_requested_permissions = True
if permission_section == "requested" and line.startswith(" "):
details["requested_permissions"].append(stripped)
continue
if permission_section in ("declared", "install") and line.startswith(
" "
):
details["permissions"].append(
cls._permission(stripped, permission_section)
)
continue
if (
permission_section == "runtime"
and line.startswith(" ")
and current_user is not None
):
current_user["permissions"].append(cls._permission(stripped, "runtime"))
continue
simple_match = re.match(
r"(appId|userId|versionName|timeStamp|lastUpdateTime|installerPackageName)=(.*)",
stripped,
)
if simple_match:
key = {
"appId": "app_id",
"userId": "app_id",
"versionName": "version_name",
"timeStamp": "timestamp",
"lastUpdateTime": "last_update_time",
"installerPackageName": "installer",
}[simple_match.group(1)]
raw_value = simple_match.group(2)
details[key] = (
_value(raw_value)
if key == "app_id" or raw_value == "null"
else raw_value
)
continue
if stripped.startswith("pkgFlags="):
details["system"] = "SYSTEM" in stripped.split("=", 1)[1].split()
continue
version_match = re.match(
r"versionCode=([^\s]+)(?:\s+minSdk=([^\s]+))?(?:\s+targetSdk=([^\s]+))?",
stripped,
)
if version_match:
details["version_code"] = _value(version_match.group(1))
details["min_sdk"] = (
_value(version_match.group(2)) if version_match.group(2) else None
)
details["target_sdk"] = (
_value(version_match.group(3)) if version_match.group(3) else None
)
elif stripped.startswith("firstInstallTime="):
legacy_first_install = stripped.split("=", 1)[1]
if legacy_first_install:
user_zero = next(
(user for user in details["users"] if user["user_id"] == 0), None
)
if user_zero is None:
user_zero = {"user_id": 0, "permissions": []}
details["users"].append(user_zero)
user_zero.setdefault("first_install_time", legacy_first_install)
return details
def parse(self, content: str) -> None:
self.results: list[dict[str, Any]] = []
category: str | None = None
package: dict[str, Any] | None = None
block: list[str] = []
def parse_dumpsys_packages(self, output: str) -> List[Dict[str, Any]]:
"""
Parse the dumpsys package service data
"""
pkg_rxp = re.compile(r" Package \[(.+?)\].*")
def finish() -> None:
nonlocal package, block
if package is not None:
package.update(self.parse_dumpsys_package_for_details("\n".join(block)))
self.results.append(package)
package = None
block = []
results = []
package_name = None
package = {}
lines: list[str] = []
for line in output.splitlines():
if line.startswith(" Package ["):
if len(lines) > 0:
details = self.parse_dumpsys_package_for_details("\n".join(lines))
package.update(details)
results.append(package)
lines = []
package = {}
matches = pkg_rxp.findall(line)
if not matches:
continue
package_name = matches[0]
package["package_name"] = package_name
continue
if not package_name:
continue
lines.append(line)
if len(lines) > 0:
details = self.parse_dumpsys_package_for_details("\n".join(lines))
package.update(details)
results.append(package)
return results
def parse(self, content: str):
"""
Parse the Dumpsys Package section for activities
Adds results to self.results
:param content: content of the package section (string)
"""
self.results = []
package = []
in_package_list = False
for line in content.splitlines():
if line == "Packages:":
finish()
category = "active"
if line.startswith("Packages:"):
in_package_list = True
continue
if line == "Hidden system packages:":
finish()
category = "hidden_system"
if not in_package_list:
continue
package_match = re.match(r"^ Package \[([^]]+)\]", line)
if package_match and category:
finish()
package = {
"package_name": package_match.group(1),
"package_type": category,
}
continue
if (
category
and line
and not line.startswith(" ")
and not line.endswith(" overlay paths:")
):
finish()
category = None
continue
if package is not None:
block.append(line)
finish()
if line.strip() == "":
break
package.append(line)
self.results = self.parse_dumpsys_packages("\n".join(package))
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import re
from .artifact import AndroidArtifact
@@ -27,37 +25,19 @@ class DumpsysPlatformCompatArtifact(AndroidArtifact):
def parse(self, data: str) -> None:
for line in data.splitlines():
match = re.match(r"ChangeId\((\d+);\s*(.*)\)$", line.strip())
if not match or "rawOverrides={" not in line:
if not line.startswith("ChangeId(168419799; name=DOWNSCALED;"):
continue
body = match.group(2)
name_match = re.search(r"(?:^|;\s*)name=([^;]+)", body)
state = (
"enabled"
if re.search(r"(?:^|;\s*)enabled(?:;|$)", body)
else "disabled"
)
overridable = bool(re.search(r"(?:^|;\s*)overridable(?:;|$)", body))
overrides_field = body.split("rawOverrides={", 1)[1].split("}", 1)[0]
for entry in overrides_field.split(","):
package_name, separator, raw_value = entry.strip().partition("=")
if not separator:
continue
value: bool | int | str
if raw_value in ("true", "false"):
value = raw_value == "true"
else:
try:
value = int(raw_value)
except ValueError:
value = raw_value
self.results.append(
{
"change_id": int(match.group(1)),
"change_name": name_match.group(1) if name_match else None,
"change_state": state,
"overridable": overridable,
"package_name": package_name,
"override_value": value,
}
)
if line.strip() == "":
break
# Look for rawOverrides field
if "rawOverrides={" in line:
# Extract the content inside the braces for rawOverrides
overrides_field = line.split("rawOverrides={", 1)[1].split("};", 1)[0]
for entry in overrides_field.split(", "):
# Extract app name
uninstall_app = entry.split("=")[0].strip()
self.results.append({"package_name": uninstall_app})
+108 -39
View File
@@ -4,7 +4,6 @@
# https://license.mvt.re/1.1/
from .artifact import AndroidArtifact
from .package_resolvers import parse_resolver_table
INTENT_NEW_OUTGOING_SMS = "android.provider.Telephony.NEW_OUTGOING_SMS"
INTENT_SMS_RECEIVED = "android.provider.Telephony.SMS_RECEIVED"
@@ -19,45 +18,115 @@ class DumpsysReceiversArtifact(AndroidArtifact):
"""
def check_indicators(self) -> None:
for receiver in self.results:
intent = receiver["key"]
if intent == INTENT_NEW_OUTGOING_SMS:
self.log.info(
'Found a receiver to intercept outgoing SMS messages: "%s"',
receiver["component"],
)
elif intent == INTENT_SMS_RECEIVED:
self.log.info(
'Found a receiver to intercept incoming SMS messages: "%s"',
receiver["component"],
)
elif intent == INTENT_DATA_SMS_RECEIVED:
self.log.info(
'Found a receiver to intercept incoming data SMS message: "%s"',
receiver["component"],
)
elif intent == INTENT_PHONE_STATE:
self.log.info(
'Found a receiver monitoring telephony state/incoming calls: "%s"',
receiver["component"],
)
elif intent == INTENT_NEW_OUTGOING_CALL:
self.log.info(
'Found a receiver monitoring outgoing calls: "%s"',
receiver["component"],
)
for intent, receivers in self.results.items():
for receiver in receivers:
if intent == INTENT_NEW_OUTGOING_SMS:
self.log.info(
'Found a receiver to intercept outgoing SMS messages: "%s"',
receiver["receiver"],
)
elif intent == INTENT_SMS_RECEIVED:
self.log.info(
'Found a receiver to intercept incoming SMS messages: "%s"',
receiver["receiver"],
)
elif intent == INTENT_DATA_SMS_RECEIVED:
self.log.info(
'Found a receiver to intercept incoming data SMS message: "%s"',
receiver["receiver"],
)
elif intent == INTENT_PHONE_STATE:
self.log.info(
"Found a receiver monitoring "
'telephony state/incoming calls: "%s"',
receiver["receiver"],
)
elif intent == INTENT_NEW_OUTGOING_CALL:
self.log.info(
'Found a receiver monitoring outgoing calls: "%s"',
receiver["receiver"],
)
if not self.indicators:
continue
if not self.indicators:
continue
ioc_match = self.indicators.check_app_id(receiver["package_name"])
if ioc_match:
self.alertstore.critical(
ioc_match.message,
"",
receiver,
matched_indicator=ioc_match.ioc,
)
ioc_match = self.indicators.check_app_id(receiver["package_name"])
if ioc_match:
self.alertstore.critical(
ioc_match.message,
"",
{intent: receiver},
matched_indicator=ioc_match.ioc,
)
continue
def parse(self, output: str) -> None:
self.results = parse_resolver_table(output, "Receiver")
self.results: dict[str, list[dict[str, str]]] = {}
in_receiver_resolver_table = False
in_non_data_actions = False
intent = None
for line in output.splitlines():
if line.startswith("Receiver Resolver Table:"):
in_receiver_resolver_table = True
continue
if not in_receiver_resolver_table:
continue
if line.startswith(" Non-Data Actions:"):
in_non_data_actions = True
continue
if not in_non_data_actions:
continue
# If we hit an empty line, the Non-Data Actions section should be
# finished.
if line.strip() == "":
break
# We detect the action name.
if (
line.startswith(" " * 6)
and not line.startswith(" " * 8)
and ":" in line
):
intent = line.strip().replace(":", "")
self.results[intent] = []
continue
parts = line.strip().split(" ")
if len(parts) < 2:
# A single-token line here is not a receiver. Real dumpstate
# output can print an action header mis-indented (observed with
# 15 leading spaces instead of 6), which used to raise
# IndexError and abort the whole module. Treat a trailing-colon
# token as the next action, skip anything else.
if parts[0].endswith(":"):
intent = parts[0][:-1]
self.results.setdefault(intent, [])
continue
# If we are not in an intent block yet, skip.
if not intent:
continue
# If we are in a block but the line does not start with 8 spaces
# it means the block ended a new one started, so we reset and
# continue.
if not line.startswith(" " * 8):
intent = None
continue
# If we got this far, we are processing receivers for the
# activities we are interested in.
receiver = parts[1]
package_name = receiver.split("/")[0]
self.results[intent].append(
{
"package_name": package_name,
"receiver": receiver,
}
)
+12 -9
View File
@@ -28,16 +28,19 @@ INTERESTING_PROPERTIES = [
class GetProp(AndroidArtifact):
def parse(self, entry: str) -> None:
self.results: List[Dict[str, str]] = []
# A property value may span several lines: persist.sys.boot.reason.history
# prints one boot per line. Matching the whole section instead of line by
# line lets a value run to the first closing bracket that ends a line.
rxp = re.compile(
r"^[ \t]*\[([^]]+)\]: \[(.*?)\][ \t\r]*$",
re.MULTILINE | re.DOTALL,
)
rxp = re.compile(r"\[(.+?)\]: \[(.+?)\]")
for name, value in rxp.findall(entry):
self.results.append({"name": name, "value": value})
for line in entry.splitlines():
line = line.strip()
if line == "":
continue
matches = re.findall(rxp, line)
if not matches or len(matches[0]) != 2:
continue
prop_entry = {"name": matches[0][0], "value": matches[0][1]}
self.results.append(prop_entry)
def get_device_timezone(self) -> str | None:
"""
+1 -57
View File
@@ -117,55 +117,6 @@ class Mounts(AndroidArtifact):
# Skip lines that don't match expected format
continue
@staticmethod
def parse_mountinfo(entry: str, process_id: int) -> list[dict[str, Any]]:
"""Parse Linux /proc/PID/mountinfo records."""
results = []
for line in entry.splitlines():
fields = line.split()
if "-" not in fields:
continue
separator = fields.index("-")
if separator < 6 or len(fields) < separator + 4:
continue
try:
mount_id = int(fields[0])
parent_id = int(fields[1])
except ValueError:
continue
mount_options = fields[5].split(",")
super_options = fields[separator + 3].split(",")
options = list(dict.fromkeys(mount_options + super_options))
# fields[5] are the per-mount (VFS) flags, the field after the
# separator the superblock's; a mount is writable only if both
# allow it. The merged list made every read-only overlay a HIGH.
is_read_write = "rw" in mount_options and "rw" in super_options
mount_point = fields[4].replace("\\040", " ")
device = fields[separator + 2].replace("\\040", " ")
filesystem_type = fields[separator + 1]
is_system = mount_point in SUSPICIOUS_MOUNT_POINTS or any(
mount_point.startswith(f"{prefix}/")
for prefix in SUSPICIOUS_MOUNT_POINTS
)
results.append(
{
"mount_id": mount_id,
"parent_id": parent_id,
"major_minor": fields[2],
"root": fields[3].replace("\\040", " "),
"mount_point": mount_point,
"device": device,
"filesystem_type": filesystem_type,
"mount_options": ",".join(options),
"options_list": options,
"optional_fields": fields[6:separator],
"is_system_partition": is_system,
"is_read_write": is_read_write,
"process_ids": [process_id],
}
)
return results
def check_indicators(self) -> None:
"""
Check for suspicious mount configurations that may indicate root access
@@ -195,14 +146,7 @@ class Mounts(AndroidArtifact):
)
# Check for other suspicious mount options
# `rw` sitting in the merged option list is not evidence of
# writability (see is_read_write in parse_mountinfo); every other
# suspicious option is meaningful in either list.
suspicious_opts = [
opt
for opt in options
if opt in SUSPICIOUS_OPTIONS and (opt != "rw" or mount["is_read_write"])
]
suspicious_opts = [opt for opt in options if opt in SUSPICIOUS_OPTIONS]
if suspicious_opts and mount["is_system_partition"]:
if (
"noatime" in mount["mount_options"]
@@ -1,70 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import re
RESOLVER_TYPES = {
"Full MIME Types": "full_mime_type",
"Base MIME Types": "base_mime_type",
"Wild MIME Types": "wild_mime_type",
"Schemes": "scheme",
"Non-Data Actions": "non_data_action",
"MIME Typed Actions": "mime_typed_action",
}
ENTRY_RE = re.compile(
r"^\s{8,}[0-9a-fA-F]+\s+(?P<component>\S+)"
r"(?:\s+\((?P<filters>\d+)\s+filters?\))?\s*$"
)
def parse_resolver_table(content: str, table_name: str) -> list[dict]:
"""Parse every resolver category from a dumpsys package table."""
results: list[dict] = []
in_table = False
resolver_type: str | None = None
key: str | None = None
for line in content.splitlines():
if line.startswith(f"{table_name} Resolver Table:"):
in_table = True
continue
if not in_table:
continue
if line and not line.startswith(" "):
break
section_match = re.match(r"^ {2}([^ ].*):\s*$", line)
if section_match:
resolver_type = RESOLVER_TYPES.get(section_match.group(1))
key = None
continue
if resolver_type is None:
continue
key_match = re.match(r"^ {6,}([^ ].*):\s*$", line)
if key_match:
key = key_match.group(1)
continue
if key is None:
continue
entry_match = ENTRY_RE.match(line)
if not entry_match:
continue
component = entry_match.group("component")
results.append(
{
"resolver_type": resolver_type,
"key": key,
"package_name": component.split("/", 1)[0],
"component": component,
"filter_count": int(entry_match.group("filters") or 1),
}
)
return results
+54 -73
View File
@@ -1,91 +1,72 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Copyright (c) 2021-2023 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from .artifact import AndroidArtifact
FIELD_NAMES = {
"LABEL": "label",
"USER": "user",
"PID": "pid",
"TID": "tid",
"PPID": "ppid",
"VSZ": "virtual_memory_size",
"RSS": "resident_set_size",
"WCHAN": "wchan",
"ADDR": "address",
"S": "state",
"PRI": "priority",
"NI": "nice",
"RTPRIO": "realtime_priority",
"SCH": "scheduler",
"PCY": "policy",
"TIME": "cpu_time",
"CMD": "command",
"NAME": "command",
}
INTEGER_FIELDS = {
"pid",
"tid",
"ppid",
"virtual_memory_size",
"resident_set_size",
"priority",
"nice",
}
class Processes(AndroidArtifact):
def parse(self, entry: str) -> None:
self.results = []
lines = [line for line in entry.splitlines() if line.strip()]
if not lines:
return
headers = lines[0].split()
if not all(header in FIELD_NAMES for header in headers):
return
for line in entry.splitlines()[1:]:
proc = line.split()
for line in lines[1:]:
values = line.split(None, len(headers) - 1)
if len(values) != len(headers):
# Skip empty lines
if len(proc) == 0:
continue
result = {}
valid = True
for header, raw in zip(headers, values):
key = FIELD_NAMES[header]
value: str | int = raw.strip("[]") if key == "command" else raw
if key in INTEGER_FIELDS:
try:
value = int(value)
except ValueError:
valid = False
break
result[key] = value
if valid:
self.results.append(result)
# Sometimes WCHAN is empty.
if len(proc) == 8:
proc = proc[:5] + [""] + proc[5:]
# Sometimes there is the security label.
if proc[0].startswith("u:r"):
label = proc[0]
proc = proc[1:]
else:
label = ""
# Sometimes there is no WCHAN.
if len(proc) < 9:
proc = proc[:5] + [""] + proc[5:]
self.results.append(
{
"user": proc[0],
"pid": int(proc[1]),
"ppid": int(proc[2]),
"virtual_memory_size": int(proc[3]),
"resident_set_size": int(proc[4]),
"wchan": proc[5],
"aprocress": proc[6],
"stat": proc[7],
"proc_name": proc[8].strip("[]"),
"label": label,
}
)
def check_indicators(self) -> None:
if not self.indicators:
return
for result in self.results:
command = result.get("command", "")
if not isinstance(command, str):
proc_name = result.get("proc_name", "")
if not proc_name:
continue
process_name = command.rsplit("/", 1)[-1]
if not process_name or process_name == "gatekeeperd":
# Skipping this process because of false positives.
if result["proc_name"] == "gatekeeperd":
continue
for checker in (
self.indicators.check_app_id,
self.indicators.check_process,
):
ioc_match = checker(process_name)
if ioc_match:
self.alertstore.critical(
ioc_match.message,
"",
result,
matched_indicator=ioc_match.ioc,
)
break
ioc_match = self.indicators.check_app_id(proc_name)
if ioc_match:
self.alertstore.critical(
ioc_match.message, "", result, matched_indicator=ioc_match.ioc
)
continue
ioc_match = self.indicators.check_process(proc_name)
if ioc_match:
self.alertstore.critical(
ioc_match.message, "", result, matched_indicator=ioc_match.ioc
)
+17 -241
View File
@@ -3,13 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import re
from datetime import datetime
from typing import Optional, Sequence
from mvt.common.module_types import ModuleAtomicResult, ModuleSerializedResult
from mvt.common.utils import convert_datetime_to_iso
from .artifact import AndroidArtifact
ANDROID_DANGEROUS_SETTINGS = [
@@ -65,240 +58,23 @@ ANDROID_DANGEROUS_SETTINGS = [
},
]
# dumpsys prints the fields of a setting record, and of a change history entry,
# always in this order and separated by a single space. After the value come
# `default:` and `defaultSystemSet:` when a default is recorded, then `tag:`;
# some vendor builds add whether the value survives a restore, either as
# `isValuePreservedInRestore:` or as a bare `notPreservedInRestore` token.
SETTING_FIELDS = (
"_id",
"name",
"pkg",
"value",
"default",
"defaultSystemSet",
"tag",
"isValuePreservedInRestore",
)
HISTORY_FIELDS = ("time", "mode", "oldValue", "newValue", "package")
NAMESPACE_PATTERN = re.compile(
r"^(CONFIG|GLOBAL|SECURE|SYSTEM) SETTINGS \(user (\d+)\)$"
)
SECTION_END_PATTERN = re.compile(r"ending at: (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})")
class Settings(AndroidArtifact):
"""Parser for the `dumpsys settings` output.
Every row of the settings provider becomes one result, keeping the fields
dumpsys prints alongside the value: the row id, the package which recorded
the setting, the default, the tag, and the change history. A setting name
can appear more than once within a namespace, so results are a list rather
than a mapping.
"""
def serialize(self, result: ModuleAtomicResult) -> ModuleSerializedResult:
records = []
for entry in result.get("history", []):
if not entry.get("timestamp"):
continue
records.append(
{
"timestamp": entry["timestamp"],
"module": self.__class__.__name__,
"event": "settings_change",
"data": (
f"{result.get('namespace')} setting "
f'"{result.get("name")}" changed from '
f'"{entry.get("oldValue")}" to "{entry.get("newValue")}" '
f"by {entry.get('pkg')}"
),
}
)
return records
def check_indicators(self) -> None:
for result in self.results:
name = result.get("name")
value = result.get("value")
for danger in ANDROID_DANGEROUS_SETTINGS:
# Check if one of the dangerous settings is using an unsafe
# value (different than the one specified).
if danger["key"] != name or danger["safe_value"] == value:
continue
history = result.get("history") or []
self.alertstore.medium(
f'Found suspicious "{result.get("namespace")}" setting '
f'"{name} = {value}" ({danger["description"]})',
history[-1]["timestamp"] if history else "",
result,
)
break
def parse(self, content: str) -> None:
self.results: list[ModuleAtomicResult] = []
section_end = self._parse_section_end(content)
namespace: Optional[str] = None
user: Optional[str] = None
record_lines: list[str] = []
history_lines: list[str] = []
in_history = False
def flush() -> None:
nonlocal record_lines, history_lines, in_history
if record_lines:
self.results.append(
self._build_record(
namespace, user, record_lines, history_lines, section_end
)
)
record_lines = []
history_lines = []
in_history = False
for line in content.splitlines():
heading = NAMESPACE_PATTERN.match(line.strip())
if heading:
flush()
namespace = heading.group(1).lower()
user = heading.group(2)
continue
if line.startswith("--------- "):
# dumpsys closes every section with a duration trailer.
flush()
namespace = None
continue
if namespace is None:
continue
if not line.strip():
# dumpsys prints a blank line after every namespace block and
# after a change history, and other dumps such as the
# generation registry follow the last block, so a blank line
# closes the record being read.
flush()
continue
if line.startswith("_id:"):
flush()
record_lines = [line]
continue
if not record_lines:
continue
stripped = line.strip()
if stripped.startswith("History ("):
in_history = True
continue
if in_history:
if stripped.startswith("time:"):
history_lines.append(stripped)
elif stripped and history_lines:
# A history entry can be wrapped over several lines.
history_lines[-1] += " " + stripped
continue
# Anything else continues the value of the record being read.
record_lines.append(line)
flush()
@staticmethod
def _split_fields(text: str, keys: Sequence[str]) -> dict[str, str]:
"""Split the `key:value` fields of one record.
Values are free-form and may contain spaces and newlines, so a field
runs up to the start of the next key which is actually present. Keys
dumpsys did not print are skipped.
"""
fields: dict[str, str] = {}
key = keys[0]
if not text.startswith(f"{key}:"):
return fields
remainder = text[len(key) + 1 :]
for next_key in keys[1:]:
value, separator, rest = remainder.partition(f" {next_key}:")
if separator:
fields[key] = value
key, remainder = next_key, rest
fields[key] = remainder
return fields
@staticmethod
def _parse_section_end(content: str) -> Optional[datetime]:
"""Return the time the settings section was dumped, if reported."""
match = SECTION_END_PATTERN.search(content)
if not match:
return None
try:
return datetime.strptime(match.group(1), "%Y-%m-%d %H:%M:%S")
except ValueError:
return None
@staticmethod
def _resolve_timestamp(
value: str, section_end: Optional[datetime]
) -> Optional[str]:
"""Add the missing year to a `MM-DD HH:MM:SS.mmm` history timestamp.
dumpsys prints the change history without a year, so it is resolved
against the time the section was dumped: the most recent matching date
at or before that time.
"""
if section_end is None:
return None
try:
partial = datetime.strptime(value, "%m-%d %H:%M:%S.%f")
timestamp = partial.replace(year=section_end.year)
if timestamp > section_end:
timestamp = partial.replace(year=section_end.year - 1)
except ValueError:
return None
return convert_datetime_to_iso(timestamp)
def _parse_history(
self, line: str, section_end: Optional[datetime]
) -> ModuleAtomicResult:
fields = self._split_fields(line, HISTORY_FIELDS)
return {
"timestamp": self._resolve_timestamp(fields.get("time", ""), section_end),
"oldValue": fields.get("oldValue"),
"newValue": fields.get("newValue"),
"pkg": fields.get("package"),
}
def _build_record(
self,
namespace: Optional[str],
user: Optional[str],
record_lines: list[str],
history_lines: list[str],
section_end: Optional[datetime],
) -> ModuleAtomicResult:
text = "\n".join(record_lines).rstrip()
# The bare `notPreservedInRestore` token has no `key:` shape and is
# printed last, so peel it off before splitting the fields.
head = text.removesuffix(" notPreservedInRestore")
record: ModuleAtomicResult = {"namespace": namespace, "user": user}
record.update(self._split_fields(head, SETTING_FIELDS))
if head != text:
record["isValuePreservedInRestore"] = "false"
record["history"] = [
self._parse_history(entry, section_end) for entry in history_lines
]
return record
for namespace, settings in self.results.items():
for key, value in settings.items():
for danger in ANDROID_DANGEROUS_SETTINGS:
# Check if one of the dangerous settings is using an unsafe
# value (different than the one specified).
if danger["key"] == key and danger["safe_value"] != value:
self.alertstore.medium(
f'Found suspicious "{namespace}" setting "{key} = {value}" ({danger["description"]})',
"",
{
"namespace": namespace,
"key": key,
"value": value,
"description": danger["description"],
},
)
break
+10 -36
View File
@@ -34,7 +34,6 @@ TOMBSTONE_TEXT_KEY_MAPPINGS = {
"signal": "signal_info",
"code": "code",
"Cause": "cause",
"Abort message": "abort_message",
}
@@ -68,8 +67,6 @@ class TombstoneCrashResult(pydantic.BaseModel):
uid: int
signal_info: SignalInfo
cause: Optional[str] = None
causes: Optional[List[dict]] = None
abort_message: Optional[str] = None
extra: Optional[str] = None
@@ -131,13 +128,6 @@ class TombstoneCrashArtifact(AndroidArtifact):
self, file_name: str, file_timestamp: datetime.datetime, data: bytes
) -> None:
"""Parse Android tombstone crash files from a protobuf object."""
self.results.append(self.parse_protobuf_record(file_name, file_timestamp, data))
def parse_protobuf_record(
self, file_name: str, file_timestamp: datetime.datetime, data: bytes
) -> dict:
if not data:
raise ValueError("empty protobuf tombstone")
tombstone_pb = Tombstone().parse(data)
tombstone_dict = tombstone_pb.to_dict(
casing=betterproto2.Casing.SNAKE, include_default_values=True
@@ -150,31 +140,20 @@ class TombstoneCrashArtifact(AndroidArtifact):
tombstone_dict["file_name"] = file_name
tombstone_dict["file_timestamp"] = convert_datetime_to_iso(file_timestamp)
tombstone_dict["process_name"] = self._proccess_name_from_thread(tombstone_dict)
if isinstance(tombstone_dict.get("selinux_label"), str):
tombstone_dict["selinux_label"] = tombstone_dict["selinux_label"].rstrip(
"\x00"
)
# Confirm the tombstone is valid, and matches the output model
tombstone = TombstoneCrashResult.model_validate(tombstone_dict)
return tombstone.model_dump()
self.results.append(tombstone.model_dump())
def parse(
self, file_name: str, file_timestamp: datetime.datetime, content: bytes
) -> None:
"""Parse text Android tombstone crash files."""
self.results.append(self.parse_text_record(file_name, file_timestamp, content))
def parse_text_record(
self, file_name: str, file_timestamp: datetime.datetime, content: bytes
) -> dict:
if not content:
raise ValueError("empty plaintext tombstone")
tombstone_dict = {
"file_name": file_name,
"file_timestamp": convert_datetime_to_iso(file_timestamp),
}
lines = content.decode("utf-8", errors="replace").splitlines()
lines = content.decode("utf-8").splitlines()
for line_num, line in enumerate(lines, 1):
if not line.strip() or TOMBSTONE_DELIMITER in line:
continue
@@ -189,7 +168,7 @@ class TombstoneCrashArtifact(AndroidArtifact):
# Validate the tombstone and add it to the results
tombstone = TombstoneCrashResult.model_validate(tombstone_dict)
return tombstone.model_dump()
self.results.append(tombstone.model_dump())
def _parse_tombstone_line(
self, line: str, key: str, destination_key: str, tombstone: dict
@@ -209,18 +188,11 @@ class TombstoneCrashArtifact(AndroidArtifact):
def _load_key_value_line(
self, line: str, key: str, destination_key: str, tombstone: dict
) -> bool:
# The caller matched the key as a bare prefix, so a longer word starting
# with it arrives here: `Caused by: …` inside an abort message reaches
# the `Cause` key. That is a different line, not a broken file — say so
# by declining it, and let the remaining keys have their turn. Raising
# here discarded the whole tombstone, crash and stack trace included.
line_key, separator, value = line.partition(":")
if not separator or line_key != key:
return False
line_key, value = line.split(":", 1)
if line_key != key:
raise ValueError(f"Expected key {key}, got {line_key}")
value_clean = value.strip()
if len(value_clean) >= 2 and value_clean[0] == value_clean[-1] == "'":
value_clean = value_clean[1:-1]
value_clean = value.strip().strip("'")
if destination_key == "uid":
tombstone[destination_key] = int(value_clean)
elif destination_key == "process_uptime":
@@ -294,7 +266,9 @@ class TombstoneCrashArtifact(AndroidArtifact):
@staticmethod
def _parse_timestamp_string(timestamp: str) -> str:
timestamp_parsed = parser.parse(timestamp)
return convert_datetime_to_iso(timestamp_parsed)
# Preserve the source wall-clock time while returning the project-wide ISO format.
local_timestamp = timestamp_parsed.replace(tzinfo=datetime.timezone.utc)
return convert_datetime_to_iso(local_timestamp)
@staticmethod
def _proccess_name_from_thread(tombstone_dict: dict) -> str:
+79 -90
View File
@@ -8,11 +8,12 @@ from zipfile import BadZipFile
import click
from mvt.common.cli_plugins import (
ANDROID_CLI_PLUGIN_GROUP,
MVT_ANDROID_CUSTOM_COMMANDS_ENV,
load_cli_commands_option,
register_cli_plugins,
from mvt.common.cmd_check_iocs import CmdCheckIOCS
from mvt.common.completion import (
SUPPORTED_SHELLS,
completion_instructions,
generate_completion_script,
install_completion_script,
)
from mvt.common.help import (
HELP_MSG_ANDROID_BACKUP_PASSWORD,
@@ -24,6 +25,7 @@ from mvt.common.help import (
HELP_MSG_CHECK_IOCS,
HELP_MSG_CHECK_INTRUSION_LOGS,
HELP_MSG_DELAY_CHECKS,
HELP_MSG_COMPLETION,
HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
HELP_MSG_DISABLE_UPDATE_CHECK,
HELP_MSG_HASHES,
@@ -35,16 +37,23 @@ from mvt.common.help import (
HELP_MSG_OUTPUT,
HELP_MSG_STIX2,
HELP_MSG_VERBOSE,
HELP_MSG_VERBOSE_COMMAND,
HELP_MSG_VERSION,
HELP_MSG_VIRUS_TOTAL,
)
from mvt.common.logo import logo
from mvt.common.module_loader import CustomModuleLoadError, load_custom_modules
from mvt.common.updates import IndicatorsUpdates
from mvt.common.utils import init_logging, set_verbose_logging
# The commands import what they run only when they are invoked. This module is
# imported at every start of mvt-android, including by shell completion on
# every keystroke, so importing it must do no more than build the command tree:
# the forensic modules, the backup parsers and the update checks stay out of it.
from .cmd_check_androidqf import CmdAndroidCheckAndroidQF
from .cmd_check_backup import CmdAndroidCheckBackup
from .cmd_check_bugreport import CmdAndroidCheckBugreport
from .cmd_check_intrusion_logs import CmdAndroidCheckIntrusionLogs
from .modules.intrusion_logs import INTRUSION_LOGS_MODULES
from .modules.androidqf import ANDROIDQF_MODULES
from .modules.backup import BACKUP_MODULES
from .modules.backup.helpers import cli_load_android_backup_password
from .modules.bugreport import BUGREPORT_MODULES
init_logging()
log = logging.getLogger("mvt")
@@ -62,14 +71,7 @@ def _get_disable_flags(ctx):
)
def _get_verbose(ctx):
"""Return whether --verbose was passed to the CLI itself."""
return bool(ctx.obj and ctx.obj.get("verbose", False))
def _load_custom_modules(load_module):
from mvt.common.module_loader import CustomModuleLoadError, load_custom_modules
try:
return load_custom_modules(load_module)
except CustomModuleLoadError as exc:
@@ -80,7 +82,6 @@ def _load_custom_modules(load_module):
# Main
# ==============================================================================
@click.group(invoke_without_command=False)
@load_cli_commands_option
@click.option(
"--disable-update-check", is_flag=True, help=HELP_MSG_DISABLE_UPDATE_CHECK
)
@@ -89,31 +90,60 @@ def _load_custom_modules(load_module):
is_flag=True,
help=HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.pass_context
def cli(ctx, disable_update_check, disable_indicator_update_check, verbose):
def cli(ctx, disable_update_check, disable_indicator_update_check):
ctx.ensure_object(dict)
ctx.obj["disable_version_check"] = disable_update_check
ctx.obj["disable_indicator_check"] = disable_indicator_update_check
ctx.obj["verbose"] = verbose
set_verbose_logging(verbose)
from mvt.common.logo import logo
logo(
disable_version_check=disable_update_check,
disable_indicator_check=disable_indicator_update_check,
)
if ctx.invoked_subcommand != "completion":
logo(
disable_version_check=disable_update_check,
disable_indicator_check=disable_indicator_update_check,
)
# ==============================================================================
# Command: version
# ==============================================================================
@cli.command("version", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_VERSION)
@cli.command("version", help=HELP_MSG_VERSION)
def version():
return
# ==============================================================================
# Command: completion
# ==============================================================================
@cli.command("completion", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_COMPLETION)
@click.argument("shell", required=False, type=click.Choice(SUPPORTED_SHELLS))
@click.option(
"--install",
is_flag=True,
help="Write completion files and update shell configuration.",
)
@click.pass_context
def completion(ctx, shell, install):
program_name = "mvt-android"
if shell is None:
if install:
raise click.UsageError("A shell is required when using --install.")
click.echo(completion_instructions(program_name))
return
root_cli = ctx.find_root().command
if install:
script_path = install_completion_script(root_cli, program_name, shell)
click.echo(f"Installed {shell} completion to {script_path}")
if shell in ("bash", "zsh"):
click.echo(f"Updated ~/.{shell}rc")
else:
click.echo("Fish loads completion files automatically.")
return
click.echo(generate_completion_script(root_cli, program_name, shell))
# ==============================================================================
# Command: check-adb (removed)
# ==============================================================================
@@ -150,17 +180,7 @@ def check_adb(ctx):
default=[],
help=HELP_MSG_LOAD_MODULE,
)
@click.option(
"--timezone",
"-t",
default=None,
help=(
"IANA timezone name for the device, for example 'Europe/Paris'. "
"Bugreport file timestamps are the device's wall clock; by default the "
"zone is read from persist.sys.timezone in the bugreport itself."
),
)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("BUGREPORT_PATH", type=click.Path(exists=True))
@click.pass_context
def check_bugreport(
@@ -170,26 +190,17 @@ def check_bugreport(
list_modules,
module,
load_module,
timezone,
verbose,
bugreport_path,
):
from .cmd_check_bugreport import CmdAndroidCheckBugreport
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
custom_modules = _load_custom_modules(load_module)
module_options = {}
if timezone:
module_options["device_timezone"] = timezone
# Always generate hashes as bug reports are small.
cmd = CmdAndroidCheckBugreport(
target_path=bugreport_path,
results_path=output,
ioc_files=iocs,
module_name=module,
module_options=module_options if module_options else None,
hashes=True,
disable_version_check=_get_disable_flags(ctx)[0],
disable_indicator_check=_get_disable_flags(ctx)[1],
@@ -200,6 +211,8 @@ def check_bugreport(
cmd.list_modules()
return
log.info("Checking Android bug report at path: %s", bugreport_path)
try:
cmd.run()
except BadZipFile as exc:
@@ -235,7 +248,7 @@ def check_bugreport(
)
@click.option("--non-interactive", "-n", is_flag=True, help=HELP_MSG_NONINTERACTIVE)
@click.option("--backup-password", "-p", help=HELP_MSG_ANDROID_BACKUP_PASSWORD)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("BACKUP_PATH", type=click.Path(exists=True))
@click.pass_context
def check_backup(
@@ -249,10 +262,7 @@ def check_backup(
verbose,
backup_path,
):
from .cmd_check_backup import CmdAndroidCheckBackup
from .modules.backup.helpers import cli_load_android_backup_password
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
custom_modules = _load_custom_modules(load_module)
# Always generate hashes as backups are generally small.
@@ -274,6 +284,8 @@ def check_backup(
cmd.list_modules()
return
log.info("Checking Android backup at path: %s", backup_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_support_message()
@@ -310,7 +322,7 @@ def check_backup(
)
@click.option("--non-interactive", "-n", is_flag=True, help=HELP_MSG_NONINTERACTIVE)
@click.option("--backup-password", "-p", help=HELP_MSG_ANDROID_BACKUP_PASSWORD)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("ANDROIDQF_PATH", type=click.Path(exists=True))
@click.pass_context
def check_androidqf(
@@ -328,10 +340,7 @@ def check_androidqf(
verbose,
androidqf_path,
):
from .cmd_check_androidqf import CmdAndroidCheckAndroidQF
from .modules.backup.helpers import cli_load_android_backup_password
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
custom_modules = _load_custom_modules(load_module)
cmd = CmdAndroidCheckAndroidQF(
@@ -355,6 +364,8 @@ def check_androidqf(
cmd.list_modules()
return
log.info("Checking AndroidQF acquisition at path: %s", androidqf_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_disable_adb_warning()
@@ -397,7 +408,7 @@ def check_androidqf(
"time instead of UTC."
),
)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("LOGS_PATH", type=click.Path(exists=True))
@click.pass_context
def check_intrusion_logs(
@@ -411,9 +422,7 @@ def check_intrusion_logs(
verbose,
logs_path,
):
from .cmd_check_intrusion_logs import CmdAndroidCheckIntrusionLogs
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
custom_modules = _load_custom_modules(load_module)
module_options = {}
@@ -435,6 +444,8 @@ def check_intrusion_logs(
cmd.list_modules()
return
log.info("Checking intrusion logs at path: %s", logs_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_support_message()
@@ -464,10 +475,6 @@ def check_intrusion_logs(
@click.argument("FOLDER", type=click.Path(exists=True))
@click.pass_context
def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
from mvt.common.cmd_check_iocs import CmdCheckIOCS
from .command_modules import ANDROID_CHECK_IOCS_MODULES
custom_modules = _load_custom_modules(load_module)
cmd = CmdCheckIOCS(
target_path=folder,
@@ -478,7 +485,9 @@ def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
custom_modules=custom_modules,
platform="android",
)
cmd.modules = ANDROID_CHECK_IOCS_MODULES
cmd.modules = (
BACKUP_MODULES + BUGREPORT_MODULES + ANDROIDQF_MODULES + INTRUSION_LOGS_MODULES
)
if list_modules:
cmd.list_modules()
@@ -494,25 +503,5 @@ def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
# ==============================================================================
@cli.command("download-iocs", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_STIX2)
def download_indicators():
from mvt.common.updates import IndicatorsUpdates
ioc_updates = IndicatorsUpdates()
ioc_updates.update()
# ==============================================================================
# Entry point of the mvt-android console script
# ==============================================================================
def main() -> None:
"""Register the external commands and run the mvt-android CLI.
External commands are registered here rather than when this module is
imported, so that importing MVT never runs third-party code and a plugin
importing from MVT cannot re-enter a module that is still initializing.
"""
register_cli_plugins(
cli,
entry_point_group=ANDROID_CLI_PLUGIN_GROUP,
environment_variable=MVT_ANDROID_CUSTOM_COMMANDS_ENV,
)
cli()
+3 -48
View File
@@ -3,7 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import json
import logging
import os
import shutil
@@ -82,8 +81,6 @@ class CmdAndroidCheckAndroidQF(Command):
if not self.target_path:
raise NoAndroidQFTargetPath
self.log.info("Checking AndroidQF acquisition at path: %s", self.target_path)
if os.path.isdir(self.target_path):
self.__format = "dir"
parent_path = Path(self.target_path).absolute().parent.as_posix()
@@ -97,47 +94,6 @@ class CmdAndroidCheckAndroidQF(Command):
self.__zip = zipfile.ZipFile(self.target_path)
self.__files = self.__zip.namelist()
self._load_acquisition_context()
def _load_acquisition_context(self) -> None:
"""Pass AndroidQF acquisition metadata to nested commands and modules."""
context = {}
metadata_files = [
file_path
for file_path in self.__files
if file_path.replace("\\", "/").rsplit("/", 1)[-1] == "acquisition.json"
]
for file_path in metadata_files:
try:
metadata = json.loads(self._get_file_content(file_path))
if isinstance(metadata, dict):
context["started"] = metadata.get("started")
context["adb_host_public_key"] = metadata.get("adb_host_public_key")
break
except (json.JSONDecodeError, OSError, TypeError, UnicodeDecodeError):
self.log.warning(
'Unable to read AndroidQF acquisition metadata "%s"', file_path
)
if not context.get("adb_host_public_key"):
key_files = [
file_path
for file_path in self.__files
if file_path.replace("\\", "/").rsplit("/", 1)[-1] == "adb_host_key.pub"
]
for file_path in key_files:
try:
context["adb_host_public_key"] = self._get_file_content(
file_path
).decode("utf-8")
break
except (OSError, UnicodeDecodeError):
self.log.warning(
'Unable to read AndroidQF ADB host key "%s"', file_path
)
self.module_options["androidqf_acquisition"] = context
def module_init(self, module: AndroidQFModule) -> None: # type: ignore[override]
if self.__format == "zip" and self.__zip:
module.from_zip(self.__zip, self.__files)
@@ -264,7 +220,6 @@ class CmdAndroidCheckAndroidQF(Command):
cmd.run()
self.timeline.extend(cmd.timeline)
self.url_results.extend(cmd.url_results)
self.alertstore.extend(cmd.alertstore.alerts)
finally:
if bugreport:
@@ -294,13 +249,14 @@ class CmdAndroidCheckAndroidQF(Command):
try:
cmd.from_ab(backup)
except InvalidAndroidBackup as exc:
self.log.warning("Skipping backup modules: %s", exc)
self.log.warning(
"Skipping backup modules as backup.ab is malformed: %s", exc
)
return False
cmd.run()
self.timeline.extend(cmd.timeline)
self.url_results.extend(cmd.url_results)
self.alertstore.extend(cmd.alertstore.alerts)
return True
@@ -380,7 +336,6 @@ class CmdAndroidCheckAndroidQF(Command):
cmd.run()
self.timeline.extend(cmd.timeline)
self.url_results.extend(cmd.url_results)
self.alertstore.extend(cmd.alertstore.alerts)
return True
-5
View File
@@ -87,15 +87,11 @@ class CmdAndroidCheckBackup(Command):
if header["encryption"] != "none":
password = prompt_or_load_android_backup_password(log, self.module_options)
if not password:
if self.sub_command:
raise InvalidAndroidBackup("No backup password provided")
log.critical("No backup password provided.")
sys.exit(1)
try:
tardata = parse_backup_file(ab_file_bytes, password=password)
except InvalidBackupPassword:
if self.sub_command:
raise InvalidAndroidBackup("Invalid backup password")
log.critical("Invalid backup password")
sys.exit(1)
except AndroidBackupParsingError as exc:
@@ -129,7 +125,6 @@ class CmdAndroidCheckBackup(Command):
assert self.target_path is not None # type: ignore[has-type]
# Use a different local variable name to avoid any scoping issues
backup_path: str = self.target_path # type: ignore[has-type]
self.log.info("Checking Android backup at path: %s", backup_path)
if os.path.isfile(backup_path):
self.__type = "ab"
+7 -99
View File
@@ -3,19 +3,13 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import fnmatch
import io
import logging
import os
from pathlib import Path
from typing import List, Optional
from zipfile import BadZipFile, ZipFile
from zipfile import ZipFile
from mvt.android.artifacts.getprop import GetProp
from mvt.android.modules.bugreport.base import (
DUMPSTATE_ENTRY_POINTS,
BugReportModule,
)
from mvt.android.modules.bugreport.base import BugReportModule
from mvt.common.command import Command
from mvt.common.indicators import Indicators
from mvt.common.module import MVTModule
@@ -93,100 +87,14 @@ class CmdAndroidCheckBugreport(Command):
for file_name in self.__zip.namelist():
self.__files.append(file_name)
if not self._has_dumpstate(self.__files):
nested = self._nested_bugreport(bugreport_zip)
if nested:
self.__zip = nested
self.__files = list(nested.namelist())
@staticmethod
def _has_dumpstate(file_names: List[str]) -> bool:
"""Whether these members carry any of the entry points the bug report
modules read (see `BugReportModule._get_dumpstate_file`)."""
return any(
fnmatch.filter(file_names, pattern) for pattern in DUMPSTATE_ENTRY_POINTS
)
def _nested_bugreport(self, outer: ZipFile) -> Optional[ZipFile]:
"""Descend one level into an OEM wrapper archive.
MIUI / HyperOS hands out a zip of app logs, ANR traces and tcpdump
captures with the real `bugreport-<device>-<timestamp>.zip` nested
inside. Without this descent the outer archive has no entry point,
every module reports it found no files, and the command still exits 0
with an empty result.
"""
candidates = [
name for name in outer.namelist() if name.lower().endswith(".zip")
]
candidates.sort(
key=lambda name: (
"bugreport" not in name.lower() and "dumpstate" not in name.lower()
)
)
for name in candidates:
try:
inner = ZipFile(io.BytesIO(outer.read(name)))
except (BadZipFile, OSError):
continue
if self._has_dumpstate(inner.namelist()):
log.info("Found the bug report nested inside the archive: %s", name)
return inner
inner.close()
return None
def init(self) -> None:
if self.target_path:
self.log.info("Checking Android bug report at path: %s", self.target_path)
if os.path.isfile(self.target_path):
self.from_zip(ZipFile(self.target_path))
elif os.path.isdir(self.target_path):
self.from_dir(self.target_path)
self.log.warning(
"Analysing an unpacked bugreport: file timestamps come from "
"the extraction, not from the device. Analyse the original "
"zip to keep the device's file timestamps."
)
if self.__format:
self._resolve_device_timezone()
def _resolve_device_timezone(self) -> None:
"""Name the device's timezone in module_options unless it is known already.
A bugreport's SYSTEM PROPERTIES section carries persist.sys.timezone.
Zip entry times are the device's wall clock, and modules read them in
this zone; --timezone or check-androidqf's own reading takes precedence.
"""
if self.module_options.get("device_timezone"):
self.log.info("Device timezone: %s", self.module_options["device_timezone"])
if not self.target_path:
return
probe = BugReportModule(log=self.log)
self.module_init(probe)
timezone = None
try:
dumpstate = probe._get_dumpstate_file()
except Exception as exc:
self.log.warning("Could not read the bugreport's dumpstate: %s", exc)
dumpstate = None
if dumpstate:
properties = GetProp()
properties.parse(
BugReportModule.extract_command_section(
dumpstate.decode("utf-8", errors="replace"),
"------ SYSTEM PROPERTIES",
)
)
timezone = properties.get_device_timezone()
if timezone:
self.log.info("Device timezone identified from the bugreport: %s", timezone)
self.module_options["device_timezone"] = timezone
else:
self.log.warning(
"persist.sys.timezone not found in the bugreport; file timestamps "
"are the device's wall clock without a timezone. Pass --timezone "
"to name it."
)
if os.path.isfile(self.target_path):
self.from_zip(ZipFile(self.target_path))
elif os.path.isdir(self.target_path):
self.from_dir(self.target_path)
def module_init(self, module: BugReportModule) -> None: # type: ignore[override]
if self.__format == "zip":
@@ -63,8 +63,6 @@ class CmdAndroidCheckIntrusionLogs(Command):
if not self.target_path:
raise ValueError("No target path specified")
self.log.info("Checking intrusion logs at path: %s", self.target_path)
if not os.path.isdir(self.target_path) and not (
os.path.isfile(self.target_path)
and self.target_path.lower().endswith(".zip")
-23
View File
@@ -1,23 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
"""Module lists an mvt-android command composes from more than one family.
Commands whose modules are one family read that family directly. check-iocs
re-checks stored results, so it has to know every module that could have
written one, and both the CLI and any other code needing that answer share
the list from here rather than each concatenating their own.
"""
from mvt.common.module import MVTModule
from .modules.androidqf import ANDROIDQF_MODULES
from .modules.backup import BACKUP_MODULES
from .modules.bugreport import BUGREPORT_MODULES
from .modules.intrusion_logs import INTRUSION_LOGS_MODULES
ANDROID_CHECK_IOCS_MODULES: list[type[MVTModule]] = (
BACKUP_MODULES + BUGREPORT_MODULES + ANDROIDQF_MODULES + INTRUSION_LOGS_MODULES
)
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .aqf_files import AQFFiles
from .aqf_getprop import AQFGetProp
from .aqf_log_timestamps import AQFLogTimestamps
@@ -14,7 +12,7 @@ from .aqf_settings import AQFSettings
from .mounts import Mounts
from .root_binaries import RootBinaries
ANDROIDQF_MODULES: list[type[MVTModule]] = [
ANDROIDQF_MODULES = [
AQFPackages,
AQFProcesses,
AQFGetProp,
@@ -3,7 +3,11 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import logging
from typing import Optional
from mvt.android.artifacts.settings import Settings as SettingsArtifact
from mvt.common.module_types import ModuleResults
from .base import AndroidQFModule
@@ -11,23 +15,43 @@ from .base import AndroidQFModule
class AQFSettings(SettingsArtifact, AndroidQFModule):
"""This module analyse setting files"""
def __init__(
self,
file_path: Optional[str] = None,
target_path: Optional[str] = None,
results_path: Optional[str] = None,
module_options: Optional[dict] = None,
log: logging.Logger = logging.getLogger(__name__),
results: Optional[ModuleResults] = None,
) -> None:
super().__init__(
file_path=file_path,
target_path=target_path,
results_path=results_path,
module_options=module_options,
log=log,
results=results,
)
self.results: dict = results if results is not None else {}
def run(self) -> None:
for setting_file in self._get_files_by_pattern("*/settings_*.txt"):
namespace = setting_file[setting_file.rfind("_") + 1 : -4]
self.results[namespace] = {}
data = self._get_file_content(setting_file)
for line in data.decode("utf-8").splitlines():
name, separator, value = line.strip().partition("=")
if not separator:
line = line.strip()
try:
key, value = line.split("=", 1)
except ValueError:
continue
self.results.append(
{
"namespace": namespace,
"user": None,
"name": name,
"value": value,
}
)
try:
self.results[namespace][key] = value
except IndexError:
continue
self.log.info("Identified %d settings", len(self.results))
self.log.info(
"Identified %d settings", sum([len(val) for val in self.results.values()])
)
+1 -3
View File
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .sms import SMS
BACKUP_MODULES: list[type[MVTModule]] = [SMS]
BACKUP_MODULES = [SMS]
-5
View File
@@ -57,11 +57,6 @@ class SMS(BackupModule):
ioc_match.message, "", message, matched_indicator=ioc_match.ioc
)
def collect_url_results(self) -> None:
for message in self.results:
for url in message.get("links", []):
self.add_url_result(url, message.get("isodate"), "sms")
def run(self) -> None:
sms_path = "apps/com.android.providers.telephony/d_f/*_sms_backup"
for file in self._get_files_by_pattern(sms_path):
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .dumpsys_accessibility import DumpsysAccessibility
from .dumpsys_activities import DumpsysActivities
from .dumpsys_appops import DumpsysAppops
@@ -18,11 +16,8 @@ from .dumpsys_receivers import DumpsysReceivers
from .dumpsys_adb_state import DumpsysADBState
from .fs_timestamps import BugReportTimestamps
from .tombstones import Tombstones
from .mounts import Mounts
from .processes import Processes
from .settings import Settings
BUGREPORT_MODULES: list[type[MVTModule]] = [
BUGREPORT_MODULES = [
DumpsysAccessibility,
DumpsysActivities,
DumpsysAppops,
@@ -36,7 +31,4 @@ BUGREPORT_MODULES: list[type[MVTModule]] = [
DumpsysADBState,
BugReportTimestamps,
Tombstones,
Processes,
Settings,
Mounts,
]
+10 -73
View File
@@ -6,23 +6,12 @@ import datetime
import fnmatch
import logging
import os
import re
from pathlib import Path
from typing import List, Optional
from zipfile import ZipFile
from zoneinfo import ZoneInfo, ZoneInfoNotFoundError
from mvt.common.module import ModuleResults, MVTModule
# `------ 0.101s was the duration of 'SOME SECTION' ------`, printed when that
# section finishes and not necessarily between two sections.
SECTION_DURATION = re.compile(r"^-{3,}\s*[0-9.]+s was the duration of", re.IGNORECASE)
# The members a bug report archive can be entered through, in the order
# _get_dumpstate_file() tries them. An archive carrying none of them is not a
# bug report at this level (see CmdAndroidCheckBugreport._has_dumpstate).
DUMPSTATE_ENTRY_POINTS = ("main_entry.txt", "dumpState_*.log", "*/dumpsys.txt")
class BugReportModule(MVTModule):
"""This class provides a base for all Android Bug Report modules."""
@@ -83,11 +72,7 @@ class BugReportModule(MVTModule):
if not self.extract_path:
raise ValueError("extract_path is not set")
joined = os.path.join(self.extract_path, file_path)
if (
not Path(joined)
.resolve()
.is_relative_to(Path(self.extract_path).resolve())
):
if not Path(joined).resolve().is_relative_to(Path(self.extract_path).resolve()):
raise ValueError("unsafe file_path")
handle = open(joined, "rb")
@@ -97,9 +82,7 @@ class BugReportModule(MVTModule):
return data
def _get_dumpstate_file(self) -> Optional[bytes]:
main_entry, dumpstate_log, dumpsys_txt = DUMPSTATE_ENTRY_POINTS
main = self._get_files_by_pattern(main_entry)
main = self._get_files_by_pattern("main_entry.txt")
if main:
main_content = self._get_file_content(main[0])
try:
@@ -107,68 +90,22 @@ class BugReportModule(MVTModule):
except KeyError:
return None
dumpstate_logs = self._get_files_by_pattern(dumpstate_log)
dumpstate_logs = self._get_files_by_pattern("dumpState_*.log")
if dumpstate_logs:
return self._get_file_content(dumpstate_logs[0])
dumpsys_files = self._get_files_by_pattern(dumpsys_txt)
dumpsys_files = self._get_files_by_pattern("*/dumpsys.txt")
if dumpsys_files:
return self._get_file_content(dumpsys_files[0])
return None
@staticmethod
def extract_command_section(content: str, heading: str) -> str:
"""Return a bugreport command section without consuming the next one.
Bugreport separators include timing text, so looking for a line equal to
``------`` is not sufficient and can accidentally feed the remainder of
dumpstate to a parser.
"""
lines: list[str] = []
in_section = False
for line in content.splitlines():
stripped = line.strip()
if not in_section:
if stripped.startswith(heading):
in_section = True
continue
if stripped.startswith("------"):
# dumpstate prints a section's timing line when that section
# finishes, which can land in the middle of the one being
# written. Treating it as a boundary truncates the section at
# an arbitrary point, silently.
if SECTION_DURATION.match(stripped):
continue
break
lines.append(line)
return "\n".join(lines)
def _device_timezone(self) -> Optional[datetime.tzinfo]:
"""The device's timezone named in module_options, or None when unknown."""
name = self.module_options.get("device_timezone")
if not name:
return None
try:
return ZoneInfo(name)
except ZoneInfoNotFoundError:
self.log.warning("Unknown device timezone %s", name)
return None
def _get_file_modification_time(self, file_path: str) -> datetime.datetime:
"""When the file was last modified.
A zip entry carries the device's wall clock, so it is returned in the
device's timezone when the bugreport names one and naive otherwise.
An unpacked bugreport's mtime is whatever the extraction left, an
instant returned in UTC.
"""
if self.zip_archive:
file_timetuple = self.zip_archive.getinfo(file_path).date_time
return datetime.datetime(*file_timetuple, tzinfo=self._device_timezone())
if not self.extract_path:
raise ValueError("extract_path is not set")
file_stat = os.stat(os.path.join(self.extract_path, file_path))
return datetime.datetime.fromtimestamp(
file_stat.st_mtime, tz=datetime.timezone.utc
)
return datetime.datetime(*file_timetuple)
else:
if not self.extract_path:
raise ValueError("extract_path is not set")
file_stat = os.stat(os.path.join(self.extract_path, file_path))
return datetime.datetime.fromtimestamp(file_stat.st_mtime)
@@ -48,28 +48,11 @@ class DumpsysAccessibility(DumpsysAccessibilityArtifact, BugReportModule):
)
self.parse(content)
listed = unnamed = enabled_count = 0
for result in self.results:
if result.get("component"):
listed += 1
enabled = result.get("enabled")
if enabled is True:
enabled_count += 1
self.log.info(
'Found accessibility service "%s" (enabled: %s)',
result.get("component"),
"not stated" if enabled is None else enabled,
)
continue
# The operator gets this per user as a LOW alert from
# check_indicators(); here it only has to survive into the summary,
# so that a stated count never reads as "a total of 0".
unnamed += result.get("unnamed_service_count") or 0
self.log.info(
'Found installed accessibility service "%s"', result.get("service")
)
self.log.info(
"Identified a total of %d accessibility services, %d reported enabled "
"(%d more stated by the dump without a component name)",
listed,
enabled_count,
unnamed,
"Identified a total of %d accessibility services", len(self.results)
)
@@ -3,15 +3,11 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import base64
import binascii
import datetime
import logging
from typing import Optional
from mvt.android.artifacts.dumpsys_adb import DumpsysADBArtifact
from mvt.common.module_types import ModuleResults
from mvt.common.utils import convert_datetime_to_iso
from .base import BugReportModule
@@ -57,122 +53,3 @@ class DumpsysADBState(DumpsysADBArtifact, BugReportModule):
"Identified a total of %d trusted ADB keys",
len(self.results[0].get("user_keys", [])),
)
@staticmethod
def _key_material(public_key: object) -> str:
if isinstance(public_key, bytes):
public_key = public_key.decode("utf-8", errors="replace")
if not isinstance(public_key, str):
return ""
return public_key.strip().split(" ", 1)[0]
@staticmethod
def _is_valid_key(public_key: str) -> bool:
if not public_key:
return False
try:
return bool(base64.b64decode(public_key, validate=True))
except (binascii.Error, ValueError):
return False
@staticmethod
def _parse_acquisition_time(value: object) -> Optional[datetime.datetime]:
if not isinstance(value, str):
return None
try:
timestamp = datetime.datetime.fromisoformat(value.replace("Z", "+00:00"))
except ValueError:
return None
if not timestamp.tzinfo:
timestamp = timestamp.replace(tzinfo=datetime.timezone.utc)
return timestamp.astimezone(datetime.timezone.utc)
@staticmethod
def _parse_last_connected(value: object) -> Optional[datetime.datetime]:
try:
return datetime.datetime.fromtimestamp(
int(str(value)) / 1000,
tz=datetime.timezone.utc,
)
except (OSError, OverflowError, TypeError, ValueError):
return None
def _trusted_keys(self) -> list[dict]:
"""Return unique trusted keys, preferring keystore connection metadata."""
trusted_keys = []
seen = set()
for result in self.results:
keystore = result.get("keystore", [])
candidates = keystore if isinstance(keystore, list) else []
candidates = [*candidates, *result.get("user_keys", [])]
for candidate in candidates:
if not isinstance(candidate, dict):
continue
key = self._key_material(candidate.get("key"))
identity = key or repr(candidate)
if identity in seen:
continue
seen.add(identity)
trusted_keys.append(candidate)
return trusted_keys
def check_indicators(self) -> None:
if "androidqf_acquisition" not in self.module_options:
return super().check_indicators()
context = self.module_options.get("androidqf_acquisition")
if not isinstance(context, dict):
context = {}
acquisition_key = self._key_material(context.get("adb_host_public_key"))
if acquisition_key and not self._is_valid_key(acquisition_key):
acquisition_key = ""
acquisition_time = self._parse_acquisition_time(context.get("started"))
cutoff = (
acquisition_time - datetime.timedelta(days=1) if acquisition_time else None
)
for trusted_key in self._trusted_keys():
key = self._key_material(trusted_key.get("key"))
fingerprint = trusted_key.get("fingerprint") or "<unknown key>"
user = trusted_key.get("user") or "unknown user"
description = f"{fingerprint} ({user})"
last_connected = self._parse_last_connected(
trusted_key.get("last_connected")
)
event_time = (
convert_datetime_to_iso(last_connected) if last_connected else ""
)
if not self._is_valid_key(key):
self.alertstore.low(
f"Found an invalid trusted ADB host key: {description}",
event_time,
trusted_key,
)
continue
if not acquisition_key:
self.alertstore.low(
"Found a trusted ADB host key, but the AndroidQF acquisition "
f"does not include its host key: {description}",
event_time,
trusted_key,
)
continue
if key != acquisition_key:
self.alertstore.low(
"Found a trusted ADB host key different from the AndroidQF "
f"acquisition host: {description}",
event_time,
trusted_key,
)
continue
if cutoff and last_connected and last_connected <= cutoff:
self.alertstore.info(
"Found a trusted ADB host key last connected at least one day "
f"before the AndroidQF acquisition: {description}",
event_time,
trusted_key,
)
@@ -44,8 +44,21 @@ class DumpsysGetProp(GetPropArtifact, BugReportModule):
)
return
section = self.extract_command_section(
content.decode(errors="ignore"), "------ SYSTEM PROPERTIES"
)
self.parse(section)
lines = []
in_getprop = False
for line in content.decode(errors="ignore").splitlines():
if line.strip().startswith("------ SYSTEM PROPERTIES"):
in_getprop = True
continue
if not in_getprop:
continue
if line.strip() == "------":
break
lines.append(line)
self.parse("\n".join(lines))
self.log.info("Extracted %d Android system properties", len(self.results))
@@ -50,10 +50,7 @@ class DumpsysPackages(DumpsysPackagesArtifact, BugReportModule):
for result in self.results:
dangerous_permissions_count = 0
permissions = list(result["permissions"])
for user in result.get("users", []):
permissions.extend(user.get("permissions", []))
for perm in permissions:
for perm in result["permissions"]:
if perm["name"] in DANGEROUS_PERMISSIONS:
dangerous_permissions_count += 1
@@ -13,7 +13,7 @@ from mvt.common.module_types import ModuleResults
class DumpsysPlatformCompat(DumpsysPlatformCompatArtifact, BugReportModule):
"""This module extracts raw per-package compatibility overrides."""
"""This module extracts details on uninstalled apps."""
def __init__(
self,
@@ -48,4 +48,4 @@ class DumpsysPlatformCompat(DumpsysPlatformCompatArtifact, BugReportModule):
)
self.parse(content)
self.log.info("Found %d package compatibility overrides", len(self.results))
self.log.info("Found %d uninstalled apps", len(self.results))
@@ -33,7 +33,7 @@ class DumpsysReceivers(DumpsysReceiversArtifact, BugReportModule):
results=results,
)
self.results = results if results else []
self.results = results if results else {}
def run(self) -> None:
content = self._get_dumpstate_file()
@@ -49,4 +49,4 @@ class DumpsysReceivers(DumpsysReceiversArtifact, BugReportModule):
)
self.parse(dumpsys_section)
self.log.info("Extracted %d package receivers", len(self.results))
self.log.info("Extracted receivers for %d intents", len(self.results))
@@ -40,29 +40,13 @@ class BugReportTimestamps(FileTimestampsArtifact, BugReportModule):
self.results = []
for file in filesystem_files:
# A zip entry keeps the device's wall clock, read in the device's
# timezone when the command found one (see CmdAndroidCheckBugreport);
# an unpacked bugreport's mtime is read as a UTC instant.
# Only the modification time is available in the zip file metadata.
# The timezone is the local timezone of the machine the phone.
modification_time = self._get_file_modification_time(file)
self.results.append(
{
"path": file,
"modified_time": convert_datetime_to_iso(
modification_time.replace(tzinfo=None)
),
"modified_time_utc": (
convert_datetime_to_iso(modification_time)
if modification_time.tzinfo
else None
),
"timezone": (
self.module_options.get("device_timezone")
if self.zip_archive
else "UTC"
),
"timestamp_source": (
"zip_metadata" if self.zip_archive else "filesystem_metadata"
),
"modified_time": convert_datetime_to_iso(modification_time),
}
)
@@ -1,41 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
import re
from mvt.android.artifacts.mounts import Mounts as MountsArtifact
from .base import BugReportModule
class Mounts(MountsArtifact, BugReportModule):
"""Extract and deduplicate process mount namespaces from mountinfo."""
def run(self) -> None:
mount_files = self._get_files_by_pattern("FS/proc/*/mountinfo")
if not mount_files:
mount_files = self._get_files_by_pattern("*/proc/*/mountinfo")
unique: dict[tuple, dict] = {}
for file_path in mount_files:
pid_match = re.search(r"/proc/(\d+)/mountinfo$", file_path)
if not pid_match:
continue
entries = self.parse_mountinfo(
self._get_file_content(file_path).decode("utf-8", errors="replace"),
int(pid_match.group(1)),
)
for entry in entries:
identity = (
entry["major_minor"],
entry["root"],
entry["mount_point"],
entry["device"],
entry["filesystem_type"],
entry["mount_options"],
)
if identity in unique:
unique[identity]["process_ids"].extend(entry["process_ids"])
else:
unique[identity] = entry
self.results = list(unique.values())
self.log.info("Extracted %d unique mount records", len(self.results))
@@ -1,22 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
from mvt.android.artifacts.processes import Processes as ProcessesArtifact
from .base import BugReportModule
class Processes(ProcessesArtifact, BugReportModule):
"""Extract the process and thread table from dumpstate."""
def run(self) -> None:
data = self._get_dumpstate_file()
if not data:
self.log.error("Unable to find dumpstate file")
return
section = self.extract_command_section(
data.decode("utf-8", errors="replace"),
"------ PROCESSES AND THREADS",
)
self.parse(section)
self.log.info("Identified %d running process threads", len(self.results))
@@ -1,21 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
from mvt.android.artifacts.settings import Settings as SettingsArtifact
from .base import BugReportModule
class Settings(SettingsArtifact, BugReportModule):
"""Extract all SettingsProvider namespaces and users."""
def run(self) -> None:
data = self._get_dumpstate_file()
if not data:
self.log.error("Unable to find dumpstate file")
return
section = self.extract_dumpsys_section(
data.decode("utf-8", errors="replace"), "DUMP OF SERVICE settings:"
)
self.parse(section)
self.log.info("Identified %d Android settings", len(self.results))
+13 -68
View File
@@ -43,76 +43,21 @@ class Tombstones(TombstoneCrashArtifact, BugReportModule):
)
return
grouped: dict[str, dict[str, str]] = {}
for file_path in tombstone_files:
file_name = file_path.rsplit("/", 1)[-1]
source = "protobuf" if file_name.endswith(".pb") else "text"
crash_id = file_name.removesuffix(".pb")
grouped.setdefault(crash_id, {})[source] = file_path
for tombstone_file in sorted(tombstone_files):
tombstone_filename = tombstone_file.split("/")[-1]
modification_time = self._get_file_modification_time(tombstone_file)
tombstone_data = self._get_file_content(tombstone_file)
for crash_id, paths in sorted(grouped.items()):
parsed_sources: dict[str, dict] = {}
source_records: dict[str, dict] = {}
for source in ("text", "protobuf"):
file_path = paths.get(source)
if file_path is None:
continue
file_name = file_path.rsplit("/", 1)[-1]
file_timestamp = self._get_file_modification_time(file_path)
source_info = {
"file_name": file_name,
"file_timestamp": file_timestamp.isoformat(),
"parsed": False,
"error": None,
"record": None,
}
try:
data = self._get_file_content(file_path)
if source == "protobuf":
record = self.parse_protobuf_record(
file_name, file_timestamp, data
)
else:
record = self.parse_text_record(file_name, file_timestamp, data)
source_info["parsed"] = True
source_info["record"] = record
source_records[source] = record
except Exception as exc:
source_info["error"] = str(exc)
self.log.error(
"Error parsing tombstone file %s: %s", file_path, exc
try:
if tombstone_file.endswith(".pb"):
self.parse_protobuf(
tombstone_filename, modification_time, tombstone_data
)
parsed_sources[source] = source_info
if not source_records:
continue
preferred = source_records.get("protobuf") or source_records["text"]
canonical = dict(preferred)
text_record = source_records.get("text")
if text_record:
for key, value in text_record.items():
if canonical.get(key) in (None, "", [], {}):
canonical[key] = value
differences = {}
protobuf_record = source_records.get("protobuf")
if text_record and protobuf_record:
for key in text_record.keys() & protobuf_record.keys():
if key in ("file_name", "file_timestamp"):
continue
if text_record[key] != protobuf_record[key]:
differences[key] = {
"text": text_record[key],
"protobuf": protobuf_record[key],
}
canonical.update(
{
"crash_id": crash_id,
"sources": parsed_sources,
"differences": differences,
}
)
self.results.append(canonical)
else:
self.parse(tombstone_filename, modification_time, tombstone_data)
except ValueError as e:
# Catch any exceptions raised during parsing or validation.
self.log.error(f"Error parsing tombstone file {tombstone_file}: {e}")
self.log.info(
"Extracted a total of %d tombstone files",
@@ -3,13 +3,11 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .connect_event import ConnectEvent
from .dns_event import DnsEvent
from .security_event import SecurityEvent
INTRUSION_LOGS_MODULES: list[type[MVTModule]] = [
INTRUSION_LOGS_MODULES = [
DnsEvent,
ConnectEvent,
SecurityEvent,
-110
View File
@@ -1,110 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import click
from mvt.common.cli_plugins import (
MVT_CUSTOM_COMMANDS_ENV,
NEUTRAL_CLI_PLUGIN_GROUP,
load_cli_commands_option,
register_cli_plugins,
)
from mvt.common.cmd_plugins import plugins
from mvt.common.completion import completion
from mvt.common.help import (
HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
HELP_MSG_DISABLE_UPDATE_CHECK,
HELP_MSG_STIX2,
HELP_MSG_VERBOSE,
HELP_MSG_VERSION,
)
from mvt.common.logo import logo
from mvt.common.updates import IndicatorsUpdates
from mvt.common.utils import init_logging, set_verbose_logging
init_logging()
CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
# ==============================================================================
# Main
# ==============================================================================
@click.group(invoke_without_command=True)
@load_cli_commands_option
@click.option(
"--disable-update-check", is_flag=True, help=HELP_MSG_DISABLE_UPDATE_CHECK
)
@click.option(
"--disable-indicator-update-check",
is_flag=True,
help=HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.pass_context
def cli(ctx, disable_update_check, disable_indicator_update_check, verbose):
"""Mobile Verification Toolkit.
The 'mvt-ios' and 'mvt-android' CLI commands are used to perform
forensic analysis on IOS and Android devices.
"""
ctx.ensure_object(dict)
ctx.obj["disable_version_check"] = disable_update_check
ctx.obj["disable_indicator_check"] = disable_indicator_update_check
ctx.obj["verbose"] = verbose
set_verbose_logging(verbose)
if ctx.invoked_subcommand != "completion":
logo(
disable_version_check=disable_update_check,
disable_indicator_check=disable_indicator_update_check,
)
if ctx.invoked_subcommand is None:
click.echo(ctx.get_help())
# ==============================================================================
# Command: download-iocs
# ==============================================================================
@cli.command("download-iocs", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_STIX2)
def download_iocs():
ioc_updates = IndicatorsUpdates()
ioc_updates.update()
# ==============================================================================
# Command: completion
# ==============================================================================
cli.add_command(completion)
# ==============================================================================
# Command: version
# ==============================================================================
@cli.command("version", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_VERSION)
def version():
return
# The plugins command is registered as a built-in command, before any external
# command, so that an installed package can never replace it.
cli.add_command(plugins)
# ==============================================================================
# Entry point of the mvt console script
# ==============================================================================
def main() -> None:
"""Register the external commands and run the mvt CLI.
External commands are registered here rather than when this module is
imported, so that importing MVT never runs third-party code and a plugin
importing from MVT cannot re-enter a module that is still initializing.
"""
register_cli_plugins(
cli,
entry_point_group=NEUTRAL_CLI_PLUGIN_GROUP,
environment_variable=MVT_CUSTOM_COMMANDS_ENV,
)
cli()
-317
View File
@@ -1,317 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import hashlib
import importlib.metadata
import importlib.util
import logging
import os
import sys
from pathlib import Path
from types import ModuleType
from typing import Iterable
import click
# This module is imported by every CLI at start-up, and by shell completion on
# every keystroke, so it must stay cheap: nothing here may import the module
# machinery (mvt.common.module_loader and what it pulls in).
IOS_CLI_PLUGIN_GROUP = "mvt.ios.cli_plugins"
ANDROID_CLI_PLUGIN_GROUP = "mvt.android.cli_plugins"
# Commands in this group are registered on the platform-neutral mvt command only.
NEUTRAL_CLI_PLUGIN_GROUP = "mvt.cli_plugins"
MVT_CUSTOM_COMMANDS_ENV = "MVT_CUSTOM_COMMANDS"
MVT_IOS_CUSTOM_COMMANDS_ENV = "MVT_IOS_CUSTOM_COMMANDS"
MVT_ANDROID_CUSTOM_COMMANDS_ENV = "MVT_ANDROID_CUSTOM_COMMANDS"
# Prefix of the import name given to a command file loaded from a path. Shared
# with module_loader, which recognises such files when naming their loggers.
CUSTOM_COMMAND_MODULE_PREFIX = "_mvt_custom_command_"
log = logging.getLogger(__name__)
class CustomCommandLoadError(Exception):
pass
class BrokenPluginCommand(click.Command):
"""A placeholder for an installed or configured command that failed to load."""
def __init__(self, name: str, source: str, exception: BaseException):
super().__init__(
name,
help=(
f"Unable to load external command from {source}.\n\n"
f"{type(exception).__name__}: {exception}"
),
short_help="Warning: external command could not be loaded.",
)
self.source = source
self.exception = exception
def parse_args(self, ctx: click.Context, args: list[str]) -> list[str]:
return args
def invoke(self, ctx: click.Context) -> None:
raise click.ClickException(
f"Unable to load external command '{self.name}' from {self.source}: "
f"{type(self.exception).__name__}: {self.exception}"
)
def _module_name_for_path(path: Path) -> str:
digest = hashlib.sha256(str(path).encode("utf-8")).hexdigest()[:16]
return f"{CUSTOM_COMMAND_MODULE_PREFIX}{path.stem}_{digest}"
def _iter_command_files(path: Path) -> Iterable[Path]:
if path.is_file():
if path.suffix != ".py":
raise CustomCommandLoadError(
f"Custom command file is not a Python file: {path}"
)
yield path
return
if path.is_dir():
for child in sorted(path.iterdir()):
if child.name.startswith(".") or child.name == "__init__.py":
continue
if child.is_file() and child.suffix == ".py":
yield child
return
raise CustomCommandLoadError(f"Custom command path does not exist: {path}")
def _load_python_file(path: Path) -> ModuleType:
module_name = _module_name_for_path(path)
spec = importlib.util.spec_from_file_location(module_name, path)
if spec is None or spec.loader is None:
raise CustomCommandLoadError(f"Unable to load custom command file: {path}")
module = importlib.util.module_from_spec(spec)
sys.modules[module_name] = module
try:
spec.loader.exec_module(module)
except (Exception, SystemExit) as exc:
raise CustomCommandLoadError(
f"Unable to import custom command {path}: {exc}"
) from exc
return module
def load_cli_command_file(path: Path) -> click.Command:
module = _load_python_file(path)
command = getattr(module, "cli", None)
if not isinstance(command, click.Command):
raise CustomCommandLoadError(
f"Custom command {path} must export a Click command or group named 'cli'"
)
if command.name is None:
raise CustomCommandLoadError(f"Custom command {path} has no command name")
return command
def _register_command(
group: click.Group,
command: click.Command,
*,
name: str,
source: str,
collision_is_error: bool,
) -> bool:
if name in group.commands:
registered_sources = getattr(group, "_mvt_external_command_sources", {})
if registered_sources.get(name) == source:
return False
message = (
f"Unable to register external command '{name}' from {source}: "
"the command name is already registered"
)
if collision_is_error:
raise CustomCommandLoadError(message)
log.warning(message)
return False
group.add_command(command, name=name)
registered_sources = getattr(group, "_mvt_external_command_sources", {})
registered_sources[name] = source
setattr(group, "_mvt_external_command_sources", registered_sources)
return True
def register_cli_commands_from_path(
group: click.Group,
path: str | Path,
*,
collision_is_error: bool = False,
failures_are_errors: bool = False,
) -> list[str]:
resolved_path = Path(path).expanduser().resolve()
registered: list[str] = []
try:
command_files = list(_iter_command_files(resolved_path))
except CustomCommandLoadError as exc:
if failures_are_errors:
raise
name = resolved_path.stem.replace("_", "-") or "custom-command"
if _register_command(
group,
BrokenPluginCommand(name, str(resolved_path), exc),
name=name,
source=str(resolved_path),
collision_is_error=collision_is_error,
):
registered.append(name)
return registered
for command_file in command_files:
try:
command = load_cli_command_file(command_file)
except CustomCommandLoadError as exc:
if failures_are_errors:
raise
name = command_file.stem.replace("_", "-")
command = BrokenPluginCommand(name, str(command_file), exc)
command_name = command.name
if command_name is None:
raise CustomCommandLoadError(
f"Custom command {command_file} has no command name"
)
if _register_command(
group,
command,
name=command_name,
source=str(command_file),
collision_is_error=collision_is_error,
):
registered.append(command_name)
return registered
def _entry_point_source(entry_point: importlib.metadata.EntryPoint) -> str:
try:
distribution = getattr(entry_point, "dist", None)
if distribution is None:
return f"entry point {entry_point.value}"
name = distribution.metadata.get("Name", "unknown distribution")
version = getattr(distribution, "version", None)
if version:
return f"{name} {version} ({entry_point.value})"
return f"{name} ({entry_point.value})"
except Exception:
return f"entry point {entry_point.value}"
def register_installed_cli_commands(
group: click.Group,
entry_point_group: str,
) -> list[str]:
try:
entry_points = importlib.metadata.entry_points(group=entry_point_group)
except Exception as exc:
log.warning(
"Unable to discover external commands in entry-point group %s: %s",
entry_point_group,
exc,
)
return []
ordered_entry_points = sorted(
entry_points,
key=lambda entry_point: (
entry_point.name,
_entry_point_source(entry_point),
entry_point.value,
),
)
registered: list[str] = []
for entry_point in ordered_entry_points:
source = _entry_point_source(entry_point)
try:
command = entry_point.load()
if not isinstance(command, click.Command):
raise TypeError(
f"entry point must resolve to a Click command or group, "
f"not {type(command).__name__}"
)
except (Exception, SystemExit) as exc:
command = BrokenPluginCommand(entry_point.name, source, exc)
if _register_command(
group,
command,
name=entry_point.name,
source=source,
collision_is_error=False,
):
registered.append(entry_point.name)
return registered
def register_cli_plugins(
group: click.Group,
*,
entry_point_group: str,
environment_variable: str,
) -> None:
"""Register the external commands of one CLI on its group.
Each CLI has one entry-point group and one environment variable of its
own, so a command package chooses the CLIs its commands are added to.
:param group: CLI group to register the external commands on.
:param entry_point_group: Entry-point group of the CLI.
:param environment_variable: Name of the environment variable holding a
path to load commands from.
"""
environment_path = os.environ.get(environment_variable)
if environment_path:
register_cli_commands_from_path(group, environment_path)
register_installed_cli_commands(group, entry_point_group)
def _load_command_option_callback(
ctx: click.Context,
param: click.Parameter,
paths: tuple[str, ...],
) -> tuple[str, ...]:
if not isinstance(ctx.command, click.Group):
raise click.ClickException("--load-command requires a Click command group")
for path in paths:
try:
register_cli_commands_from_path(
ctx.command,
path,
collision_is_error=True,
failures_are_errors=True,
)
except CustomCommandLoadError as exc:
raise click.BadParameter(str(exc), ctx=ctx, param=param) from exc
return paths
load_cli_commands_option = click.option(
"--load-command",
"load_commands",
type=click.Path(exists=True),
multiple=True,
expose_value=False,
is_eager=True,
callback=_load_command_option_callback,
help=(
"Load a custom CLI command from a Python file or folder "
"(can be invoked multiple times)"
),
)
+3 -8
View File
@@ -9,7 +9,6 @@ from typing import Optional
from mvt.common.command import Command
from mvt.common.module import MVTModule
from mvt.common.module_loader import get_module_logger
from mvt.common.utils import exec_or_profile
log = logging.getLogger(__name__)
@@ -56,10 +55,6 @@ class CmdCheckIOCS(Command):
if entry not in all_modules:
all_modules.append(entry)
# Read the indicators once, so that a missing indicators file is
# reported even when no stored result matches a module.
iocs = self.iocs
log.info("Checking stored results against provided indicators...")
total_detections = 0
@@ -81,14 +76,14 @@ class CmdCheckIOCS(Command):
)
m = iocs_module.from_json(
file_path, log=get_module_logger(iocs_module)
file_path, log=logging.getLogger(iocs_module.__module__)
)
if not m:
log.warning("No result from this module, skipping it")
continue
if iocs.total_ioc_count > 0:
m.indicators = iocs
if self.iocs.total_ioc_count > 0:
m.indicators = self.iocs
m.indicators.log = m.log
try:
-205
View File
@@ -1,205 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import importlib.metadata
import logging
from typing import Optional
import click
from rich.console import Console
from rich.table import Table
from .cli_plugins import (
ANDROID_CLI_PLUGIN_GROUP,
IOS_CLI_PLUGIN_GROUP,
NEUTRAL_CLI_PLUGIN_GROUP,
)
from .config import settings
from .help import (
HELP_MSG_PLUGINS,
HELP_MSG_PLUGINS_CHECK_UPDATES,
HELP_MSG_PLUGINS_LIST,
)
from .module import MVTModule
from .module_loader import MODULES_ENTRY_POINT_GROUP, distribution_direct_url
from .updates import (
SHORT_COMMIT_LENGTH,
PluginUpdates,
installed_plugin_distributions,
)
log = logging.getLogger(__name__)
CLI_PLUGIN_GROUPS = (
IOS_CLI_PLUGIN_GROUP,
ANDROID_CLI_PLUGIN_GROUP,
NEUTRAL_CLI_PLUGIN_GROUP,
)
CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
def _entry_points(group: str) -> list[importlib.metadata.EntryPoint]:
try:
return list(importlib.metadata.entry_points(group=group))
except Exception as exc:
log.warning("Unable to discover the entry points in group %s: %s", group, exc)
return []
def _entry_point_distribution(
entry_point: importlib.metadata.EntryPoint,
) -> Optional[str]:
dist = getattr(entry_point, "dist", None)
if dist is None:
return None
try:
return dist.name
except Exception:
return None
def _distribution_version(dist: importlib.metadata.Distribution) -> str:
try:
return dist.version or "unknown"
except Exception:
return "unknown"
def _distribution_origin(dist: importlib.metadata.Distribution) -> str:
"""Describe where a plugin package was installed from."""
direct_url = distribution_direct_url(dist)
if direct_url is None:
return "pypi"
vcs_info = direct_url.get("vcs_info")
if isinstance(vcs_info, dict):
commit = vcs_info.get("commit_id") or ""
if commit:
return f"git+{commit[:SHORT_COMMIT_LENGTH]}"
return "git"
return "local"
def _contributed_modules(
entry_points: list[importlib.metadata.EntryPoint], distribution: str
) -> str:
"""Count the forensic modules a plugin package contributes.
Entry points are resolved the way MVT resolves them when it loads
modules, but a broken entry point is reported instead of raising: listing
the installed plugins must work even when one of them is faulty.
"""
count = 0
broken = False
for entry_point in entry_points:
if _entry_point_distribution(entry_point) != distribution:
continue
try:
loaded = entry_point.load()
if callable(loaded) and not isinstance(loaded, type):
loaded = loaded()
count += sum(
1
for module in loaded
if isinstance(module, type) and issubclass(module, MVTModule)
)
except (Exception, SystemExit) as exc:
log.debug(
"Unable to load the modules of entry point %s (%s): %s",
entry_point.name,
entry_point.value,
exc,
)
broken = True
if broken:
return f"{count} (error)" if count else "error"
return str(count)
def _contributed_commands(
entry_points: list[importlib.metadata.EntryPoint], distribution: str
) -> str:
names = {
entry_point.name
for entry_point in entry_points
if _entry_point_distribution(entry_point) == distribution
}
return ", ".join(sorted(names)) if names else "-"
@click.group("plugins", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_PLUGINS)
def plugins() -> None:
pass
@plugins.command("list", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_PLUGINS_LIST)
def list_plugins() -> None:
distributions = installed_plugin_distributions()
if not distributions:
click.echo("No MVT plugins are installed.")
return
module_entry_points = _entry_points(MODULES_ENTRY_POINT_GROUP)
command_entry_points = []
for group in CLI_PLUGIN_GROUPS:
command_entry_points.extend(_entry_points(group))
table = Table(title="Installed MVT plugins")
table.add_column("Name", style="bold")
table.add_column("Version")
table.add_column("Origin")
table.add_column("Modules", justify="right")
table.add_column("Commands")
for dist in distributions:
name = dist.name
table.add_row(
name,
_distribution_version(dist),
_distribution_origin(dist),
_contributed_modules(module_entry_points, name),
_contributed_commands(command_entry_points, name),
)
Console().print(table)
@plugins.command(
"check-updates",
context_settings=CONTEXT_SETTINGS,
help=HELP_MSG_PLUGINS_CHECK_UPDATES,
short_help="Check the installed plugins for updates",
)
def check_plugin_updates() -> None:
if not settings.NETWORK_ACCESS_ALLOWED:
click.echo(
"Network access is disabled, cannot check for plugin updates. "
"Enable NETWORK_ACCESS_ALLOWED in the MVT configuration to check."
)
return
if not installed_plugin_distributions():
click.echo("No MVT plugins are installed.")
return
findings = PluginUpdates().check()
if not findings:
click.echo("All plugins are up to date.")
return
click.echo("Plugin updates available:")
for finding in findings:
click.echo(f" {finding['name']} {finding['installed']} → {finding['latest']}")
click.echo(f" Upgrade with: {finding['upgrade_command']}")
click.echo(
"\nMVT does not install plugin updates. Run the command above when you "
"decide to upgrade."
)
+41 -425
View File
@@ -8,7 +8,6 @@ import logging
import os
import sys
from datetime import datetime
from functools import cached_property
from heapq import heappop, heappush
from typing import Any, Optional
@@ -20,13 +19,8 @@ from .alerts import AlertLevel, AlertStore
from .config import settings
from .indicators import Indicators
from .module import EncryptedBackupError, MVTModule, run_module, save_timeline
from .module_loader import (
ModuleOrigin,
get_module_logger,
get_module_origin,
module_supports_command,
)
from .module_types import ModuleTimeline, URLResult
from .module_loader import module_supports_command
from .module_types import ModuleTimeline
from .utils import (
CustomJSONEncoder,
convert_datetime_to_iso,
@@ -73,30 +67,25 @@ class Command:
# down a password to decrypt a backup or flags which are need by some modules.
self.module_options = module_options if module_options else {}
# This dictionary maps the modules which were replaced by a module
# declaring `replaces` to the module which took their place.
self.module_replacements: dict[type[MVTModule], type[MVTModule]] = {}
# This list will contain all executed modules.
# We can use this to reference e.g. self.executed[0].results.
self.executed: list[MVTModule] = []
self.hashes = hashes
self.hash_values: list[dict[str, Any]] = []
self.timeline: ModuleTimeline = []
self.url_results: list[URLResult] = []
# Load IOCs
self._create_storage()
self._setup_logging()
if iocs is not None:
self.iocs = iocs
else:
self.iocs = Indicators(self.log)
self.iocs.load_indicators_files(self.ioc_files)
self.alertstore = AlertStore()
@cached_property
def iocs(self) -> Indicators:
"""Load indicators on first use. Nested commands share their parent's."""
iocs = Indicators(self.log)
iocs.load_indicators_files(self.ioc_files)
return iocs
def _create_storage(self) -> None:
if self.results_path and not os.path.exists(self.results_path):
try:
@@ -161,14 +150,6 @@ class Command:
with open(alerts_path, "w+", encoding="utf-8") as handle:
json.dump(alerts, handle, indent=4, cls=CustomJSONEncoder)
def _store_urls(self) -> None:
if not self.results_path or not self.url_results:
return
urls_path = os.path.join(self.results_path, "urls.json")
with open(urls_path, "w", encoding="utf-8") as handle:
json.dump(self.url_results, handle, indent=4, cls=CustomJSONEncoder)
def _store_alerts_timeline(self) -> None:
if not self.results_path:
return
@@ -220,34 +201,10 @@ class Command:
for file in generate_hashes_from_path(self.target_path, self.log):
self.hash_values.append(file)
@staticmethod
def _modules_by_origin(
modules: list[type[MVTModule]],
) -> dict[ModuleOrigin, list[str]]:
origins: dict[ModuleOrigin, list[str]] = {}
for module in modules:
origins.setdefault(get_module_origin(module), []).append(module.__name__)
return origins
def list_modules(self) -> None:
self.log.info("Following is the list of available %s modules:", self.name)
for origin, module_names in self._modules_by_origin(
self._available_modules()
).items():
self.log.info(
" - Modules from %s: %s", origin.label, ", ".join(module_names)
)
def _log_loaded_modules(self, modules: list[type[MVTModule]]) -> None:
"""Record the loaded modules and their origins for auditability."""
for origin, module_names in self._modules_by_origin(modules).items():
self.log.info(
"Loaded %d %s modules from %s: %s",
len(module_names),
self.name,
origin.label,
", ".join(module_names),
)
for module in self._available_modules():
self.log.info(" - %s", module.__name__)
def _available_modules(self) -> list[type[MVTModule]]:
modules = list(self.modules)
@@ -262,174 +219,7 @@ class Command:
if module not in deduplicated:
deduplicated.append(module)
available = self._apply_replacements(deduplicated)
self._warn_about_slug_collisions(available)
return available
def _warn_about_slug_collisions(self, modules: list[type[MVTModule]]) -> None:
"""Report modules writing their results to the same file.
Results are stored in a file named after the module slug, so two
modules sharing one silently overwrite each other. Replacements are
already resolved here, so a module deliberately taking over the slug
of the module it replaces is not reported: the module it replaced is
no longer part of the run.
"""
modules_by_slug: dict[str, type[MVTModule]] = {}
for module in modules:
slug = module.get_slug()
first = modules_by_slug.setdefault(slug, module)
if first is module:
continue
self.log.warning(
"Modules %s from %s and %s from %s both use the slug %s. If "
"both run, whichever runs last overwrites the results of the "
"other in %s.json.",
first.__name__,
get_module_origin(first).label,
module.__name__,
get_module_origin(module).label,
slug,
slug,
)
def _declared_replacements(
self, modules: list[type[MVTModule]]
) -> dict[type[MVTModule], type[MVTModule]]:
"""Return the replacements declared by the given modules."""
replacements: dict[type[MVTModule], type[MVTModule]] = {}
for module in modules:
replaced = module.replaces
if replaced is None or replaced is module:
continue
if not module.enabled:
# Replacing a module must not disable it, as a disabled
# replacement never runs in its place.
self.log.debug(
"Module %s is disabled and does not replace module %s.",
module.__name__,
replaced.__name__,
)
continue
if replaced not in modules:
# A module can support several commands while the module it
# replaces is only available in some of them.
self.log.debug(
"Module %s replaces module %s, which is not available "
"for the %s command.",
module.__name__,
replaced.__name__,
self.name,
)
continue
if replaced in replacements:
self.log.warning(
"Modules %s and %s both replace module %s. Both of them "
"will run, %s will not, and modules depending on %s will "
"use the results of %s. Replacements which share the slug "
"of %s overwrite each other's results file.",
replacements[replaced].__name__,
module.__name__,
replaced.__name__,
replaced.__name__,
replaced.__name__,
replacements[replaced].__name__,
replaced.__name__,
)
continue
replacements[replaced] = module
return replacements
def _drop_replacement_cycles(
self, replacements: dict[type[MVTModule], type[MVTModule]]
) -> None:
"""Undo the replacements between modules which replace each other."""
cyclic: set[type[MVTModule]] = set()
for replaced in replacements:
walked: list[type[MVTModule]] = []
module = replaced
while module in replacements and module not in cyclic:
if module in walked:
cyclic.update(walked[walked.index(module) :])
break
walked.append(module)
module = replacements[module]
if not cyclic:
return
self.log.warning(
"Modules %s replace each other in a cycle. None of them replaces "
"anything and all of them will run.",
", ".join(sorted(module.__name__ for module in cyclic)),
)
for module in cyclic:
replacements.pop(module, None)
def _log_replacement(
self,
replaced: type[MVTModule],
module: type[MVTModule],
replacement: type[MVTModule],
) -> None:
"""Report an applied replacement, and any problem with it."""
if not issubclass(module, replaced):
self.log.warning(
"Module %s replaces module %s but is not a subclass of it. "
"Its results might not be compatible with what modules "
"depending on %s expect.",
module.__name__,
replaced.__name__,
replaced.__name__,
)
if replaced in module.dependencies:
self.log.warning(
"Module %s depends on module %s, which it also replaces. The "
"dependency cannot be satisfied: a replacement has to produce "
"that data itself.",
module.__name__,
replaced.__name__,
)
self.log.info(
"Module %s from %s replaces module %s from %s.",
replacement.__name__,
get_module_origin(replacement).label,
replaced.__name__,
get_module_origin(replaced).label,
)
def _apply_replacements(
self, modules: list[type[MVTModule]]
) -> list[type[MVTModule]]:
"""Drop the modules superseded by a module declaring `replaces`."""
declared = self._declared_replacements(modules)
self._drop_replacement_cycles(declared)
replacements: dict[type[MVTModule], type[MVTModule]] = {}
for replaced, module in declared.items():
# Follow chains of replacements, so that a dependency on a
# replaced module always resolves to a module which is part of
# the run.
replacement = module
while replacement in declared:
replacement = declared[replacement]
# Only the replacements which are applied are reported, so that
# the record matches the modules which actually run.
self._log_replacement(replaced, module, replacement)
replacements[replaced] = replacement
self.module_replacements = replacements
return [module for module in modules if module not in replacements]
return deduplicated
def init(self) -> None:
raise NotImplementedError
@@ -489,196 +279,42 @@ class Command:
console.print("")
console.print(panel)
def _module_dependencies(
self, module: type[MVTModule]
) -> list[tuple[type[MVTModule], type[MVTModule]]]:
"""Return the (declared, resolved) dependencies of a module.
A dependency on a module which was replaced is resolved to the module
which took its place. A module which replaces one of its own
dependencies is not made to depend on itself, while a module which
declares itself as a dependency is left alone and still fails the
circular dependency check.
"""
dependencies = []
for dependency in module.dependencies:
resolved = self.module_replacements.get(dependency, dependency)
if resolved is module and dependency is not module:
continue
dependencies.append((dependency, resolved))
return dependencies
@staticmethod
def _dependency_name(
declared: type[MVTModule], resolved: type[MVTModule]
) -> str:
"""Return how a dependency is named in the messages about it.
A dependency is named as the module which declared it wrote it, and,
when that module was replaced, as the module which runs in its place.
"""
if declared is resolved:
return declared.__name__
return f"{resolved.__name__} (replacing module {declared.__name__})"
def _selected_modules(
self, modules: list[type[MVTModule]]
) -> Optional[list[type[MVTModule]]]:
"""Return the modules explicitly requested, or all the enabled ones.
Returns None when a module was requested by name and no module of
that name can be run.
"""
if not self.module_name:
return [module for module in modules if module.enabled]
selected = [
module for module in modules if module.__name__ == self.module_name
]
# A module replacing another one does not have to keep its name, so
# the name of a replaced module selects its replacement.
if not selected:
for replaced, replacement in self.module_replacements.items():
if replaced.__name__ != self.module_name or replacement in selected:
continue
self.log.info(
"Module %s was replaced by module %s, which is run "
"in its place.",
replaced.__name__,
replacement.__name__,
)
selected.append(replacement)
if not selected:
self.log.warning(
"No module named %s is available for the %s command. "
"No modules will be run.",
self.module_name,
self.name,
)
return None
return selected
def _skipped_modules(
self,
required: list[type[MVTModule]],
module_indexes: dict[type[MVTModule], int],
) -> dict[type[MVTModule], tuple[type[MVTModule], type[MVTModule]]]:
"""Return the modules to drop because a dependency is unavailable.
A module declaring a dependency this command cannot provide is unable
to run, and so is every module depending on it. Dropping only those
keeps a single wrong declaration - in a module scoped to several
commands, for example - from silencing an entire analysis.
The returned mapping gives, for each skipped module, the module which
is missing a dependency and the dependency it is missing.
"""
skipped: dict[type[MVTModule], tuple[type[MVTModule], type[MVTModule]]] = {}
# Skipping the one module a run was asked for leaves nothing to run,
# which the caller reports instead.
remainder = (
"" if self.module_name else " The rest of the analysis will still run."
)
# Skipping one module can skip the modules depending on it, which the
# pass over the module list may already have gone past, so repeat the
# pass until nothing changes.
changed = True
while changed:
changed = False
for module in required:
if module in skipped:
continue
for declared, dependency in self._module_dependencies(module):
if dependency not in module_indexes:
# A replaced dependency always resolves to a module of
# this command, so an unavailable one is always the
# module class the author declared.
skipped[module] = (module, declared)
changed = True
self.log.warning(
"Module %s will be SKIPPED: it depends on module "
"%s, which is not available in this command.%s",
module.__name__,
declared.__name__,
remainder,
)
break
if dependency in skipped:
root, missing = skipped[dependency]
skipped[module] = (root, missing)
changed = True
if dependency is root:
self.log.warning(
"Module %s will be SKIPPED: it depends on "
"module %s, itself skipped for depending on "
"unavailable module %s.%s",
module.__name__,
self._dependency_name(declared, dependency),
missing.__name__,
remainder,
)
else:
self.log.warning(
"Module %s will be SKIPPED: it depends on "
"skipped module %s, in a chain starting at "
"module %s, which depends on unavailable "
"module %s.%s",
module.__name__,
self._dependency_name(declared, dependency),
root.__name__,
missing.__name__,
remainder,
)
break
return skipped
def _ordered_modules(self) -> Optional[list[type[MVTModule]]]:
"""Return enabled modules in stable topological order."""
modules = self._available_modules()
module_indexes = {module: index for index, module in enumerate(modules)}
selected = self._selected_modules(modules)
if selected is None:
return None
if self.module_name:
selected = [
module for module in modules if module.__name__ == self.module_name
]
else:
selected = [module for module in modules if module.enabled]
required: set[type[MVTModule]] = set()
required = set(selected)
pending = list(selected)
while pending:
module = pending.pop()
if module in required:
continue
required.add(module)
for _, dependency in self._module_dependencies(module):
# Unavailable dependencies are reported by _skipped_modules().
if dependency in module_indexes:
for dependency in module.dependencies:
if dependency not in module_indexes:
self.log.warning(
"Module %s depends on unavailable module %s. "
"No modules will be run.",
module.__name__,
dependency.__name__,
)
return None
if dependency not in required:
required.add(dependency)
pending.append(dependency)
ordered_required = sorted(required, key=lambda module: module_indexes[module])
skipped = self._skipped_modules(ordered_required, module_indexes)
runnable = [module for module in ordered_required if module not in skipped]
if skipped and not runnable:
self.log.warning(
"Every selected module was skipped for an unavailable "
"dependency. No modules will be run."
)
return None
dependents: dict[type[MVTModule], list[type[MVTModule]]] = {
module: [] for module in runnable
module: [] for module in required
}
indegree = {module: 0 for module in runnable}
for module in runnable:
for _, dependency in self._module_dependencies(module):
if dependency not in indegree:
indegree = {module: 0 for module in required}
for module in required:
for dependency in module.dependencies:
if dependency not in required:
continue
dependents[dependency].append(module)
indegree[module] += 1
@@ -697,7 +333,7 @@ class Command:
if indegree[dependent] == 0:
heappush(ready, (module_indexes[dependent], dependent))
if len(ordered) != len(runnable):
if len(ordered) != len(required):
cyclic_modules = sorted(
(module.__name__ for module, count in indegree.items() if count > 0)
)
@@ -711,34 +347,19 @@ class Command:
return ordered
def run(self) -> None:
# The output folder and its command.log exist for a run, so that
# listing modules or rejecting a target leaves nothing behind.
# Resolving the module list can warn, so the log comes first.
self._create_storage()
self._setup_logging()
ordered_modules = self._ordered_modules()
if ordered_modules is None:
return
# Read the indicators once the run is certain to happen, before
# init() does any work on the target, so that a missing indicators
# file is reported first and every module gets the same object.
iocs = self.iocs
# Commands announce their target from init(), so it goes before the
# module list.
try:
self.init()
except NotImplementedError:
pass
self._log_loaded_modules(ordered_modules)
executed_by_type: dict[type[MVTModule], MVTModule] = {}
for module in ordered_modules:
module_logger = get_module_logger(module)
module_logger = logging.getLogger(module.__module__)
m = module(
target_path=self.target_path,
@@ -746,16 +367,13 @@ class Command:
module_options=self.module_options,
log=module_logger,
)
# Dependencies are keyed by the module class they declare, even
# when it was replaced, so that a module asking for the results
# of a replaced module receives those of its replacement.
m.dependency_modules = {
dependency: executed_by_type[resolved]
for dependency, resolved in self._module_dependencies(module)
dependency: executed_by_type[dependency]
for dependency in module.dependencies
}
if iocs.total_ioc_count:
m.indicators = iocs
if self.iocs.total_ioc_count:
m.indicators = self.iocs
m.indicators.log = m.log
if self.serial:
@@ -778,7 +396,6 @@ class Command:
self.executed.append(m)
executed_by_type[module] = m
self.timeline.extend(m.timeline)
self.url_results.extend(m.url_results)
self.alertstore.extend(m.alertstore.alerts)
try:
@@ -793,5 +410,4 @@ class Command:
self._store_timeline()
self._store_alerts_timeline()
self._store_alerts()
self._store_urls()
self._store_info()
+32 -89
View File
@@ -9,83 +9,34 @@ import shlex
import click
from click.shell_completion import get_completion_class
from .help import HELP_MSG_COMPLETION
SUPPORTED_SHELLS = ("bash", "zsh", "fish")
CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
COMPLETION_INSTRUCTIONS = """Shell completion for mvt, mvt-ios and mvt-android
Print one completion script covering the three commands:
mvt completion bash > ~/.mvt-complete.bash
mvt completion zsh > ~/.mvt-complete.zsh
mkdir -p ~/.config/fish/conf.d
mvt completion fish > ~/.config/fish/conf.d/mvt-completion.fish
def completion_instructions(program_name: str) -> str:
return f"""Shell completion for {program_name}
Print a completion script:
{program_name} completion bash > ~/.{program_name}-complete.bash
{program_name} completion zsh > ~/.{program_name}-complete.zsh
mkdir -p ~/.config/fish/completions
{program_name} completion fish > ~/.config/fish/completions/{program_name}.fish
Load the generated Bash script from ~/.bashrc:
[ -f ~/.mvt-complete.bash ] && . ~/.mvt-complete.bash
[ -f ~/.{program_name}-complete.bash ] && . ~/.{program_name}-complete.bash
Load the generated Zsh script from ~/.zshrc:
[ -f ~/.mvt-complete.zsh ] && . ~/.mvt-complete.zsh
[ -f ~/.{program_name}-complete.zsh ] && . ~/.{program_name}-complete.zsh
Fish loads the files in ~/.config/fish/conf.d automatically.
Fish loads completion files from ~/.config/fish/completions automatically.
To write these files and update the Bash/Zsh shell configuration automatically:
mvt completion bash --install
mvt completion zsh --install
mvt completion fish --install
To write these files and update Bash/Zsh shell configuration automatically:
{program_name} completion bash --install
{program_name} completion zsh --install
{program_name} completion fish --install
"""
def _mvt_programs() -> list[tuple[str, click.Command]]:
"""Return the console script name and CLI group of every MVT program.
The three CLIs are imported here rather than at module level: mvt.cli
imports this module while it is being defined, and generating a completion
script should not make the start-up of `mvt` import the platform CLIs.
"""
from mvt.android.cli import cli as android_cli
from mvt.cli import cli as mvt_cli
from mvt.ios.cli import cli as ios_cli
return [("mvt", mvt_cli), ("mvt-ios", ios_cli), ("mvt-android", android_cli)]
@click.command(
"completion",
context_settings=CONTEXT_SETTINGS,
help=HELP_MSG_COMPLETION,
short_help="Generate or install shell completion",
)
@click.argument("shell", required=False, type=click.Choice(SUPPORTED_SHELLS))
@click.option(
"--install",
is_flag=True,
help="Write completion files and update shell configuration.",
)
def completion(shell, install):
if shell is None:
if install:
raise click.UsageError("A shell is required when using --install.")
click.echo(COMPLETION_INSTRUCTIONS)
return
if install:
script_path = install_completion_script(shell)
click.echo(
f"Installed {shell} completion for mvt, mvt-ios and mvt-android "
f"to {script_path}"
)
if shell in ("bash", "zsh"):
click.echo(f"Updated ~/.{shell}rc")
else:
click.echo("Fish loads the files in ~/.config/fish/conf.d automatically.")
return
click.echo(generate_mvt_completion_script(shell))
def generate_completion_script(cli: click.Command, program_name: str, shell: str) -> str:
completion_class = get_completion_class(shell)
if completion_class is None:
@@ -95,49 +46,41 @@ def generate_completion_script(cli: click.Command, program_name: str, shell: str
return completion_class(cli, {}, program_name, complete_var).source()
def generate_mvt_completion_script(shell: str) -> str:
"""Return one script completing every MVT command.
Click names the completion function of each program after the program, so
the scripts of the three commands can simply be concatenated.
"""
scripts = [
generate_completion_script(cli, program_name, shell).strip("\n")
for program_name, cli in _mvt_programs()
]
return "\n\n".join(scripts)
def install_completion_script(shell: str) -> Path:
script = generate_mvt_completion_script(shell)
script_path = _completion_script_path(shell)
def install_completion_script(
cli: click.Command,
program_name: str,
shell: str,
) -> Path:
script = generate_completion_script(cli, program_name, shell)
script_path = _completion_script_path(program_name, shell)
script_path.parent.mkdir(parents=True, exist_ok=True)
script_path.write_text(f"{script}\n", encoding="utf-8")
script_path.write_text(script, encoding="utf-8")
if shell in ("bash", "zsh"):
_install_shell_source_line(shell, script_path)
_install_shell_source_line(program_name, shell, script_path)
return script_path
def _completion_script_path(shell: str) -> Path:
def _completion_script_path(program_name: str, shell: str) -> Path:
home = Path.home()
if shell == "fish":
# conf.d is sourced when the shell starts, unlike the completions
# folder, whose files fish loads on demand by command name.
return home / ".config" / "fish" / "conf.d" / "mvt-completion.fish"
return home / ".config" / "fish" / "completions" / f"{program_name}.fish"
return home / f".mvt-complete.{shell}"
return home / f".{program_name}-complete.{shell}"
def _install_shell_source_line(shell: str, script_path: Path) -> None:
def _install_shell_source_line(program_name: str, shell: str, script_path: Path) -> None:
shell_config_path = Path.home() / f".{shell}rc"
source_line = (
f"[ -f {shlex.quote(str(script_path))} ] && "
f". {shlex.quote(str(script_path))}"
)
block = f"# MVT shell completion\n{source_line}\n"
block = (
f"# MVT shell completion for {program_name}\n"
f"{source_line}\n"
)
if shell_config_path.exists():
shell_config = shell_config_path.read_text(encoding="utf-8")
+6 -11
View File
@@ -12,9 +12,7 @@ from pydantic_settings import (
YamlConfigSettingsSource,
)
# MVT_CONFIG_FOLDER in the environment relocates the settings file, so that
# a test run or a scripted install never touches the user's own.
MVT_CONFIG_FOLDER = os.environ.get("MVT_CONFIG_FOLDER") or user_config_dir("mvt")
MVT_CONFIG_FOLDER = user_config_dir("mvt")
MVT_CONFIG_PATH = os.path.join(MVT_CONFIG_FOLDER, "config.yaml")
@@ -61,16 +59,13 @@ class MVTSettings(BaseSettings):
dotenv_settings: PydanticBaseSettingsSource,
file_secret_settings: PydanticBaseSettingsSource,
) -> Tuple[PydanticBaseSettingsSource, ...]:
yaml_source = YamlConfigSettingsSource(settings_cls, MVT_CONFIG_PATH)
sources: Tuple[PydanticBaseSettingsSource, ...] = (
YamlConfigSettingsSource(settings_cls, MVT_CONFIG_PATH),
yaml_source,
init_settings,
)
# Load env variables only when asked to. initialise() constructs the
# settings once without them so that what gets written back to
# config.yaml never includes values taken from the environment.
# init_settings() returns the keyword arguments passed to the constructor.
if init_settings().get("load_env", True):
sources = (env_settings,) + sources
# Always load env variables by default
sources = (env_settings,) + sources
return sources
def save_settings(
@@ -97,7 +92,7 @@ class MVTSettings(BaseSettings):
Afterwards we load the settings again, this time including the env variables.
"""
# Construct the settings without env variables so they are not persisted.
# Set invalid env prefix to avoid loading env variables.
settings = cls(load_env=False)
settings.save_settings()
+2 -14
View File
@@ -8,7 +8,7 @@ HELP_MSG_VERSION = "Show the currently installed version of MVT"
HELP_MSG_OUTPUT = "Specify a path to a folder where you want to store JSON results"
HELP_MSG_IOC = "Path to indicators file (can be invoked multiple time)"
HELP_MSG_FAST = "Avoid running time/resource consuming features"
HELP_MSG_LIST_MODULES = "Print list of available modules and their source, then exit"
HELP_MSG_LIST_MODULES = "Print list of available modules and exit"
HELP_MSG_MODULE = "Name of a single module you would like to run instead of all"
HELP_MSG_LOAD_MODULE = (
"Load custom MVT module(s) from a Python file or folder "
@@ -17,29 +17,17 @@ HELP_MSG_LOAD_MODULE = (
HELP_MSG_NONINTERACTIVE = "Don't ask interactive questions during processing"
HELP_MSG_HASHES = "Generate hashes of all the files analyzed"
HELP_MSG_VERBOSE = "Verbose mode"
HELP_MSG_VERBOSE_COMMAND = (
"Verbose mode (kept for compatibility, pass --verbose before the command "
"name instead)"
)
HELP_MSG_CHECK_IOCS = "Compare stored JSON results to provided indicators"
HELP_MSG_STIX2 = "Download public STIX2 indicators"
HELP_MSG_DISABLE_UPDATE_CHECK = "Disable MVT version update check"
HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK = "Disable indicators update check"
HELP_MSG_COMPLETION = (
"Generate or install shell completion for mvt, mvt-ios and mvt-android"
)
HELP_MSG_PLUGINS = "Inspect the installed MVT plugin packages"
HELP_MSG_PLUGINS_LIST = "List the installed plugins and what they contribute to MVT"
HELP_MSG_PLUGINS_CHECK_UPDATES = (
"Check the installed plugins for updates without installing them"
)
HELP_MSG_COMPLETION = "Generate or install shell completion"
# IOS Specific
HELP_MSG_DECRYPT_BACKUP = "Decrypt an encrypted iTunes backup"
HELP_MSG_BACKUP_DESTINATION = (
"Path to the folder where the decrypted backup should be stored"
)
HELP_MSG_DECRYPT_JOBS = "Number of files to decrypt concurrently"
HELP_MSG_IOS_BACKUP_PASSWORD = (
"Password to use to decrypt the backup (or, set the {MVT_IOS_BACKUP_PASSWORD} "
"environment variable)"
+6 -21
View File
@@ -18,9 +18,7 @@ from appdirs import user_data_dir
from .config import settings
from .url import URL
# MVT_DATA_FOLDER in the environment relocates the downloaded indicators and
# the update-check state kept next to them.
MVT_DATA_FOLDER = os.environ.get("MVT_DATA_FOLDER") or user_data_dir("mvt")
MVT_DATA_FOLDER = user_data_dir("mvt")
MVT_INDICATORS_FOLDER = os.path.join(MVT_DATA_FOLDER, "indicators")
logger = logging.getLogger(__name__)
@@ -51,7 +49,6 @@ class Indicators:
self.log = log
self.ioc_collections: List[Dict[str, Any]] = []
self.total_ioc_count = 0
self.resolved_urls: Dict[str, str] = {}
def _load_downloaded_indicators(self) -> None:
if not os.path.isdir(MVT_INDICATORS_FOLDER):
@@ -73,9 +70,7 @@ class Indicators:
if os.path.isfile(path) and path.lower().endswith(".stix2"):
self.parse_stix2(path)
elif os.path.isdir(path):
for file in glob.glob(
os.path.join(path, "**", "*.stix2"), recursive=True
):
for file in glob.glob(os.path.join(path, "**", "*.stix2"), recursive=True):
self.parse_stix2(file)
else:
self.log.error(
@@ -444,14 +439,9 @@ class Indicators:
orig_url.url,
dest_url.url,
)
match = self.check_url(dest_url.url)
self.resolved_urls[url] = self.resolved_urls.get(
dest_url.url, dest_url.url
)
return match
return self.check_url(dest_url.url)
final_url = dest_url
self.resolved_urls[url] = final_url.url
else:
# If it's not shortened, we just use the original URL object.
final_url = orig_url
@@ -492,13 +482,6 @@ class Indicators:
return None
def get_expanded_url(self, url: str) -> Optional[str]:
"""Return the final URL recorded while checking a shortened URL."""
expanded_url = self.resolved_urls.get(url)
if expanded_url and expanded_url != url:
return expanded_url
return None
def check_urls(self, urls: list) -> Optional[IndicatorMatch]:
"""Check a list of URLs against the provided list of domain indicators.
@@ -522,7 +505,9 @@ class Indicators:
the original URL order.
"""
batches = [list(urls) if urls else [] for urls in url_batches]
unique_urls = list(dict.fromkeys(url for urls in batches for url in urls))
unique_urls = list(
dict.fromkeys(url for urls in batches for url in urls)
)
if not unique_urls:
return [None] * len(batches)
+62 -125
View File
@@ -8,125 +8,10 @@ import logging
import requests
from rich import print as rich_print
from .config import settings
from .updates import (
IndicatorsUpdates,
MVTUpdates,
PluginUpdates,
installed_plugin_distributions,
)
from .updates import IndicatorsUpdates, MVTUpdates
from .version import MVT_VERSION
def _check_version_updates(log: logging.Logger) -> None:
try:
mvt_updates = MVTUpdates()
latest_version = mvt_updates.check()
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
rich_print(
"\t[bold]Note: Could not check for MVT updates.[/bold] "
"You may be working offline. Please update MVT regularly."
)
except Exception as e:
log.error("Error encountered when trying to check latest MVT version: %s", e)
else:
if latest_version:
rich_print(
f"\t[bold]Version {latest_version} is available! "
"Upgrade mvt with `pip3 install -U mvt` or with `pipx upgrade mvt`[/bold]"
)
def _check_indicator_updates(log: logging.Logger) -> None:
ioc_updates = IndicatorsUpdates()
# Before proceeding, we check if we have downloaded an indicators index.
# If not, there's no point in proceeding with the updates check.
if ioc_updates.get_latest_update() == 0:
rich_print(
"\t[bold]You have not yet downloaded any indicators, check "
"the `download-iocs` command![/bold]"
)
return
# We only perform this check at a fixed frequency, in order to not
# overburden the user with too many lookups if the command is being run
# multiple times.
should_check, hours = ioc_updates.should_check()
if not should_check:
rich_print(
f"\tIndicators updates checked recently, next automatic check "
f"in {int(hours)} hours"
)
return
try:
ioc_to_update = ioc_updates.check()
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
rich_print(
"\t[bold]Note: Could not check for indicator updates.[/bold] "
"You may be working offline. Please update MVT indicators regularly."
)
except Exception as e:
log.error("Error encountered when trying to check latest MVT indicators: %s", e)
else:
if ioc_to_update:
rich_print(
"\t[bold]There are updates to your indicators files! "
"Run the `download-iocs` command to update![/bold]"
)
else:
rich_print("\tYour indicators files seem to be up to date.")
def _print_plugin_updates(findings: list) -> None:
if not findings:
return
rich_print("\t[bold]Plugin updates available:[/bold]")
for finding in findings:
rich_print(
f"\t {finding['name']} {finding['installed']} → "
f"{finding['latest']} ({finding['upgrade_command']})"
)
def _check_plugin_updates(log: logging.Logger) -> None:
if not settings.NETWORK_ACCESS_ALLOWED:
return
# This runs on every command, so nothing here, including reading back what
# the latest check stored, may ever interrupt MVT.
try:
distributions = installed_plugin_distributions()
# There is nothing to check when MVT was not extended with any plugin.
if not distributions:
return
plugin_updates = PluginUpdates()
# We only perform this check at a fixed frequency, in order to not
# overburden the user (and the plugin repositories) with too many
# lookups. In between checks we print the findings of the latest one,
# leaving out those which no longer apply to what is installed.
should_check, _ = plugin_updates.should_check()
if not should_check:
_print_plugin_updates(plugin_updates.current_findings(distributions))
return
findings = plugin_updates.check()
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
rich_print(
"\t[bold]Note: Could not check for plugin updates.[/bold] "
"You may be working offline. Please update your MVT plugins regularly."
)
except Exception as e:
log.error("Error encountered when trying to check MVT plugin updates: %s", e)
else:
_print_plugin_updates(findings)
def check_updates(
disable_version_check: bool = False, disable_indicator_check: bool = False
) -> None:
@@ -134,25 +19,77 @@ def check_updates(
# First we check for MVT version updates.
if not disable_version_check:
_check_version_updates(log)
try:
mvt_updates = MVTUpdates()
latest_version = mvt_updates.check()
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
rich_print(
"\t\t[bold]Note: Could not check for MVT updates.[/bold] "
"You may be working offline. Please update MVT regularly."
)
except Exception as e:
log.error(
"Error encountered when trying to check latest MVT version: %s", e
)
else:
if latest_version:
rich_print(
f"\t\t[bold]Version {latest_version} is available! "
"Upgrade mvt with `pip3 install -U mvt` or with `pipx upgrade mvt`[/bold]"
)
# Then we check for indicators files updates.
if not disable_indicator_check:
_check_indicator_updates(log)
ioc_updates = IndicatorsUpdates()
# Finally we check for updates to the installed plugin packages. MVT never
# installs an update itself, it only reports the command which does.
if not disable_version_check:
_check_plugin_updates(log)
# Before proceeding, we check if we have downloaded an indicators index.
# If not, there's no point in proceeding with the updates check.
if ioc_updates.get_latest_update() == 0:
rich_print(
"\t\t[bold]You have not yet downloaded any indicators, check "
"the `download-iocs` command![/bold]"
)
return
# We only perform this check at a fixed frequency, in order to not
# overburden the user with too many lookups if the command is being run
# multiple times.
should_check, hours = ioc_updates.should_check()
if not should_check:
rich_print(
f"\t\tIndicators updates checked recently, next automatic check "
f"in {int(hours)} hours"
)
return
try:
ioc_to_update = ioc_updates.check()
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
rich_print(
"\t\t[bold]Note: Could not check for indicator updates.[/bold] "
"You may be working offline. Please update MVT indicators regularly."
)
except Exception as e:
log.error(
"Error encountered when trying to check latest MVT indicators: %s", e
)
else:
if ioc_to_update:
rich_print(
"\t\t[bold]There are updates to your indicators files! "
"Run the `download-iocs` command to update![/bold]"
)
else:
rich_print("\t\tYour indicators files seem to be up to date.")
def logo(
disable_version_check: bool = False, disable_indicator_check: bool = False
) -> None:
rich_print("\n")
rich_print("\t[bold]MVT - Mobile Verification Toolkit[/bold]\n")
rich_print("\thttps://mvt.re")
rich_print(f"\tVersion: {MVT_VERSION}\n")
rich_print("\t[bold]MVT[/bold] - Mobile Verification Toolkit")
rich_print("\t\thttps://mvt.re")
rich_print(f"\t\tVersion: {MVT_VERSION}")
check_updates(disable_version_check, disable_indicator_check)
-33
View File
@@ -18,7 +18,6 @@ from .module_types import (
ModuleResults,
ModuleSerializedResult,
ModuleTimeline,
URLResult,
)
from .utils import CustomJSONEncoder, exec_or_profile
@@ -46,11 +45,6 @@ class MVTModule:
slug: Optional[str] = None
dependencies: Sequence[type["MVTModule"]] = ()
supported_commands: Sequence[tuple[str, str]] = ()
# A custom module can name a module class it supersedes, usually a
# built-in one. When both are available to a command, the named module is
# dropped from the run and this module takes its place, including in the
# dependencies of any other module.
replaces: Optional[type["MVTModule"]] = None
def __init__(
self,
@@ -88,7 +82,6 @@ class MVTModule:
self.results: ModuleResults = results if results is not None else []
self.timeline: ModuleTimeline = []
self.url_results: list[URLResult] = []
self.dependency_modules: Dict[type["MVTModule"], "MVTModule"] = {}
def get_dependency_results(
@@ -117,23 +110,6 @@ class MVTModule:
def check_indicators(self) -> None:
raise NotImplementedError
def collect_url_results(self) -> None:
"""Collect URL records exposed by this module."""
def add_url_result(self, url: str, timestamp: Optional[str], source: str) -> None:
expanded_url = None
if self.indicators:
expanded_url = self.indicators.get_expanded_url(url)
self.url_results.append(
{
"url": url,
"expanded_url": expanded_url,
"timestamp": timestamp,
"source": source,
}
)
def save_to_json(self) -> None:
if not self.results_path:
return
@@ -273,15 +249,6 @@ def run_module(module: MVTModule) -> None:
"The %s module produced no detections!", module.__class__.__name__
)
try:
module.collect_url_results()
except Exception as exc:
module.log.exception(
"Error when collecting URLs from module %s: %s",
module.__class__.__name__,
exc,
)
try:
module.to_timeline()
except NotImplementedError:
+6 -286
View File
@@ -4,31 +4,18 @@
# https://license.mvt.re/1.1/
import hashlib
import importlib.metadata
import importlib.util
import inspect
import json
import logging
import os
import re
import sys
from dataclasses import dataclass
from functools import lru_cache
from pathlib import Path
from types import ModuleType
from typing import Iterable, Optional
from .cli_plugins import CUSTOM_COMMAND_MODULE_PREFIX
from .module import MVTModule
from .version import MVT_VERSION
MVT_CUSTOM_MODULES_ENV = "MVT_CUSTOM_MODULES"
MODULES_ENTRY_POINT_GROUP = "mvt.modules"
EXTERNAL_LOGGER_NAMESPACE = "mvt.ext"
PLUGIN_PACKAGE_PREFIX = "mvt_plugin_"
_ORIGIN_ATTRIBUTE = "_mvt_module_origin"
_PATH_MODULE_PREFIX = "_mvt_custom_module_"
_LOADED_FILE_DIGEST = re.compile(r"_[0-9a-f]{16}$")
log = logging.getLogger(__name__)
@@ -36,109 +23,15 @@ class CustomModuleLoadError(Exception):
pass
@dataclass(frozen=True)
class ModuleOrigin:
"""Describes where a loaded module came from, for auditability.
``kind`` is one of ``builtin`` (shipped with MVT), ``package`` (loaded
from an installed package) or ``path`` (loaded from a file passed with
``--load-module`` or the environment variable).
"""
kind: str
name: str
version: Optional[str] = None
commit: Optional[str] = None
file_sha256: Optional[str] = None
@property
def label(self) -> str:
label = self.name
if self.version:
label += f"@{self.version}"
label = f"'{label}'"
if self.commit:
label += f" (commit {self.commit})"
if self.file_sha256:
label += f" (sha256: {self.file_sha256})"
return label
def _module_name_for_path(path: Path) -> str:
digest = hashlib.sha256(str(path).encode("utf-8")).hexdigest()[:16]
return f"{_PATH_MODULE_PREFIX}{path.stem}_{digest}"
def _is_builtin_logger_name(name: str) -> bool:
return name == "mvt" or name.startswith("mvt.")
def _loaded_file_stem(name: str, prefix: str) -> str:
"""Recover a loaded file's name from the import name MVT gave it."""
return _LOADED_FILE_DIGEST.sub("", name[len(prefix) :])
def _external_logger_name(name: str) -> str:
"""Return the "mvt.ext" logger name external code logs under."""
top_level, separator, rest = name.partition(".")
if top_level.startswith(PLUGIN_PACKAGE_PREFIX) and len(top_level) > len(
PLUGIN_PACKAGE_PREFIX
):
name = top_level[len(PLUGIN_PACKAGE_PREFIX) :] + separator + rest
return f"{EXTERNAL_LOGGER_NAMESPACE}.{name}"
def get_module_logger(module_class: type[MVTModule]) -> logging.Logger:
"""Return the logger a module's records should be emitted through.
Modules loaded from installed packages or file paths live outside the
"mvt" logger hierarchy, so their records would never reach the handlers
attached to the "mvt" logger and instead fall through to
logging.lastResort (which prints bare messages and drops anything below
WARNING). Their loggers are parented under the "mvt.ext" namespace,
keeping external module names from colliding with MVT's own logger
tree. File-path modules are named after their file instead of the
mangled internal import name, and packages following the recommended
"mvt_plugin_<name>" naming convention log under "mvt.ext.<name>".
"""
name = module_class.__module__
if _is_builtin_logger_name(name):
return logging.getLogger(name)
if name.startswith(_PATH_MODULE_PREFIX):
file_name = Path(get_module_origin(module_class).name).stem
return logging.getLogger(f"{EXTERNAL_LOGGER_NAMESPACE}.{file_name}")
return logging.getLogger(_external_logger_name(name))
def get_plugin_logger(name: str) -> logging.Logger:
"""Return a general logger for use in custom MVT plugins.
Call it with ``__name__``. The logger sits under "mvt.ext". That is
where get_module_logger() puts module classes. A file loaded with
--load-module or --load-command is named after the file.
"""
if _is_builtin_logger_name(name):
return logging.getLogger(name)
# A file loaded with --load-module or --load-command is imported under a
# mangled name. Log it under the file it came from. get_module_logger()
# does the same for the module classes such a file defines.
for prefix in (_PATH_MODULE_PREFIX, CUSTOM_COMMAND_MODULE_PREFIX):
if name.startswith(prefix):
stem = _loaded_file_stem(name, prefix)
return logging.getLogger(f"{EXTERNAL_LOGGER_NAMESPACE}.{stem}")
return logging.getLogger(_external_logger_name(name))
return f"_mvt_custom_module_{path.stem}_{digest}"
def _iter_module_files(path: Path) -> Iterable[Path]:
if path.is_file():
if path.suffix != ".py":
raise CustomModuleLoadError(
f"Custom module file is not a Python file: {path}"
)
raise CustomModuleLoadError(f"Custom module file is not a Python file: {path}")
yield path
return
@@ -166,9 +59,7 @@ def _load_python_file(path: Path) -> ModuleType:
try:
spec.loader.exec_module(module)
except Exception as exc:
raise CustomModuleLoadError(
f"Unable to import custom module {path}: {exc}"
) from exc
raise CustomModuleLoadError(f"Unable to import custom module {path}: {exc}") from exc
return module
@@ -193,171 +84,17 @@ def load_custom_modules_from_path(path: str) -> list[type[MVTModule]]:
resolved_path = Path(path).expanduser().resolve()
for module_file in _iter_module_files(resolved_path):
file_sha256 = hashlib.sha256(module_file.read_bytes()).hexdigest()
loaded_module = _load_python_file(module_file)
origin = ModuleOrigin(
kind="path", name=str(module_file), file_sha256=file_sha256
)
for module_class in discover_mvt_modules(loaded_module):
key = (str(module_file), module_class.__qualname__)
if key in seen:
continue
seen.add(key)
setattr(module_class, _ORIGIN_ATTRIBUTE, origin)
custom_modules.append(module_class)
return custom_modules
def _module_key(module_class: type[MVTModule]) -> tuple[str, str]:
try:
source = str(Path(inspect.getfile(module_class)).resolve())
except (OSError, TypeError):
source = module_class.__module__
return (source, module_class.__qualname__)
def distribution_direct_url(dist: importlib.metadata.Distribution) -> Optional[dict]:
"""Return the PEP 610 direct URL metadata of a distribution, if recorded.
Packages installed from an index have no direct URL metadata, while
packages installed directly from a repository or from a local folder
record where they were installed from in ``direct_url.json``.
"""
try:
direct_url_text = dist.read_text("direct_url.json")
if not direct_url_text:
return None
direct_url = json.loads(direct_url_text)
return direct_url if isinstance(direct_url, dict) else None
except Exception:
return None
def _distribution_commit(dist: importlib.metadata.Distribution) -> Optional[str]:
"""Return the VCS commit a distribution was installed from, if recorded.
Packages installed directly from a repository (``pip install git+...``)
record the commit in ``direct_url.json`` (PEP 610).
"""
vcs_info = (distribution_direct_url(dist) or {}).get("vcs_info")
if not isinstance(vcs_info, dict):
return None
commit = vcs_info.get("commit_id")
return commit if isinstance(commit, str) else None
def _entry_point_origin(entry_point: importlib.metadata.EntryPoint) -> ModuleOrigin:
name = entry_point.name
version = None
commit = None
# Manually constructed entry points have no associated distribution.
dist = getattr(entry_point, "dist", None)
if dist is not None:
try:
name = dist.name or name
version = dist.version
except Exception:
pass
commit = _distribution_commit(dist)
return ModuleOrigin(kind="package", name=name, version=version, commit=commit)
@lru_cache(maxsize=1)
def _packages_distributions() -> dict[str, list[str]]:
try:
return dict(importlib.metadata.packages_distributions())
except Exception:
return {}
def get_module_origin(module_class: type[MVTModule]) -> ModuleOrigin:
"""Return the origin of a module class for auditing purposes."""
origin = module_class.__dict__.get(_ORIGIN_ATTRIBUTE)
if isinstance(origin, ModuleOrigin):
return origin
top_level = module_class.__module__.partition(".")[0]
if top_level == "mvt":
return ModuleOrigin(kind="builtin", name="mvt", version=MVT_VERSION)
distributions = _packages_distributions().get(top_level)
if distributions:
name = distributions[0]
version = None
commit = None
try:
dist = importlib.metadata.distribution(name)
version = dist.version
commit = _distribution_commit(dist)
except Exception:
pass
return ModuleOrigin(kind="package", name=name, version=version, commit=commit)
try:
source = str(Path(inspect.getfile(module_class)).resolve())
except (OSError, TypeError):
source = module_class.__module__
return ModuleOrigin(kind="path", name=source)
def load_installed_modules() -> list[type[MVTModule]]:
"""Load MVT modules registered by installed packages.
Packages register modules in the ``mvt.modules`` entry-point group. Each
entry point must resolve to an iterable of MVTModule subclasses, or to a
callable which returns one. A broken entry point is skipped with a
warning so that a faulty plugin package cannot break MVT.
"""
try:
entry_points = importlib.metadata.entry_points(group=MODULES_ENTRY_POINT_GROUP)
except Exception as exc:
log.warning(
"Unable to discover installed module packages in entry-point group %s: %s",
MODULES_ENTRY_POINT_GROUP,
exc,
)
return []
installed_modules: list[type[MVTModule]] = []
ordered_entry_points = sorted(
entry_points, key=lambda entry_point: (entry_point.name, entry_point.value)
)
for entry_point in ordered_entry_points:
try:
loaded = entry_point.load()
if callable(loaded) and not isinstance(loaded, type):
loaded = loaded()
module_classes = list(loaded)
except (Exception, SystemExit) as exc:
log.warning(
"Unable to load modules from entry point %s (%s): %s",
entry_point.name,
entry_point.value,
exc,
)
continue
origin = _entry_point_origin(entry_point)
for module_class in module_classes:
if not (
isinstance(module_class, type) and issubclass(module_class, MVTModule)
):
log.warning(
"Entry point %s (%s) provided %r which is not an "
"MVTModule subclass",
entry_point.name,
entry_point.value,
module_class,
)
continue
setattr(module_class, _ORIGIN_ATTRIBUTE, origin)
installed_modules.append(module_class)
return installed_modules
def load_custom_modules(paths: Optional[Iterable[str]] = None) -> list[type[MVTModule]]:
search_paths: list[str] = []
env_path = os.environ.get(MVT_CUSTOM_MODULES_ENV)
@@ -368,17 +105,10 @@ def load_custom_modules(paths: Optional[Iterable[str]] = None) -> list[type[MVTM
custom_modules: list[type[MVTModule]] = []
seen: set[tuple[str, str]] = set()
for module_class in load_installed_modules():
key = _module_key(module_class)
if key in seen:
continue
seen.add(key)
custom_modules.append(module_class)
for path in search_paths:
for module_class in load_custom_modules_from_path(path):
key = _module_key(module_class)
source = Path(inspect.getfile(module_class)).resolve()
key = (str(source), module_class.__qualname__)
if key in seen:
continue
seen.add(key)
@@ -401,14 +131,4 @@ def module_supports_command(
)
return False
pairs = {tuple(entry) for entry in supported_commands}
if (platform, command) in pairs:
return True
# A module which implements check_indicators() is re-checked by check-iocs
# for its platform. It does not need to declare the check-iocs pair.
return (
command == "check-iocs"
and platform in {entry[0] for entry in pairs if entry}
and module_class.check_indicators is not MVTModule.check_indicators
)
return (platform, command) in {tuple(entry) for entry in supported_commands}
+1 -8
View File
@@ -4,7 +4,7 @@
# https://license.mvt.re/1.1/
from dataclasses import dataclass
from typing import Any, Dict, List, Optional, TypedDict, Union
from typing import Any, Dict, List, Union
# ModuleAtomicResult is a flexible dictionary that can contain any data.
@@ -22,13 +22,6 @@ ModuleAtomicResult = Dict[str, Any]
ModuleResults = Any
class URLResult(TypedDict):
url: str
expanded_url: Optional[str]
timestamp: Optional[str]
source: str
@dataclass
class ModuleAtomicTimeline:
timestamp: str
-299
View File
@@ -1,299 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import contextlib
import json
import os
import re
import tempfile
from typing import Any, ClassVar, Dict, List, Tuple, Type, TypeVar
import yaml
from appdirs import user_config_dir, user_data_dir
from pydantic import ValidationError
from pydantic_settings import (
BaseSettings,
EnvSettingsSource,
PydanticBaseSettingsSource,
SettingsConfigDict,
YamlConfigSettingsSource,
)
PLUGIN_CONFIG_FOLDER_NAME = "plugins"
# Not "plugins": on macOS the configuration and data folders are the same
# directory, and that name already holds the settings files.
PLUGIN_DATA_FOLDER_NAME = "plugin-data"
PLUGIN_ENV_PREFIX = "MVT_PLUGIN_"
PLUGIN_NAME_PATTERN = re.compile(r"[a-z0-9][a-z0-9-]*")
PluginSettingsType = TypeVar("PluginSettingsType", bound="MVTPluginSettings")
class PluginConfigLoadError(Exception):
pass
def validate_plugin_name(plugin_name: Any) -> str:
"""
Check that a plugin name is safe to use in a file name and an env variable.
:param plugin_name: Name to validate.
:returns: The validated plugin name.
"""
if not isinstance(plugin_name, str):
raise TypeError(
f"Plugin name must be a string, not {type(plugin_name).__name__}"
)
if not PLUGIN_NAME_PATTERN.fullmatch(plugin_name):
raise ValueError(
f"Invalid plugin name {plugin_name!r}: plugin names must start with a "
"lowercase letter or a digit and may only contain lowercase letters, "
"digits and dashes"
)
return plugin_name
def plugin_config_folder() -> str:
"""
Return the folder where plugins store their configuration files.
The path is resolved on every call so it always reflects the current
environment.
"""
return os.path.join(user_config_dir("mvt"), PLUGIN_CONFIG_FOLDER_NAME)
def plugin_config_path(plugin_name: str) -> str:
"""
Return the path of the configuration file of a given plugin.
:param plugin_name: Name of the plugin.
"""
return os.path.join(
plugin_config_folder(), f"{validate_plugin_name(plugin_name)}.yaml"
)
def plugin_data_folder(plugin_name: str) -> str:
"""
Return the folder where a given plugin stores its data, creating it.
Plugins should keep whatever they persist, such as caches or downloaded
artifacts, in this folder. It is created with owner-only permissions. The
path is resolved on every call so it always reflects the current
environment. A plugin with a settings class calls
`MVTPluginSettings.data_folder()` instead, which passes `plugin_name` here.
:param plugin_name: Name of the plugin.
:returns: The path of the data folder of the plugin.
"""
# Validate the name before anything is created, so an unsafe name cannot
# leave a folder behind.
name = validate_plugin_name(plugin_name)
# makedirs() applies its mode only to the last folder of the path, so
# MVT's own data folder keeps the default permissions while the two
# plugin folders are private.
data_folder = os.path.join(user_data_dir("mvt"), PLUGIN_DATA_FOLDER_NAME)
os.makedirs(data_folder, mode=0o700, exist_ok=True)
folder = os.path.join(data_folder, name)
os.makedirs(folder, mode=0o700, exist_ok=True)
return folder
def plugin_env_prefix(plugin_name: str) -> str:
"""
Return the environment variable prefix used by a given plugin.
Dashes are replaced by underscores. Plugin names cannot contain underscores,
so two different plugin names never share an environment namespace.
:param plugin_name: Name of the plugin.
"""
name = validate_plugin_name(plugin_name).upper().replace("-", "_")
return f"{PLUGIN_ENV_PREFIX}{name}_"
def _settings_plugin_name(settings_cls: Type[BaseSettings]) -> str:
plugin_name = getattr(settings_cls, "plugin_name", None)
if plugin_name is None:
raise TypeError(
f"{settings_cls.__name__} must set a 'plugin_name' class attribute to "
"namespace its configuration file and environment variables"
)
return validate_plugin_name(plugin_name)
def _plugin_yaml_source(
settings_cls: Type[BaseSettings], config_path: str
) -> YamlConfigSettingsSource:
"""
Build the YAML settings source of a plugin, reporting unusable files.
A missing file is not an error, but a file which cannot be parsed or which
does not hold a mapping of setting names is reported with its path.
"""
try:
return YamlConfigSettingsSource(settings_cls, config_path)
except yaml.YAMLError as exc:
raise PluginConfigLoadError(
f"Invalid plugin configuration file {config_path}: {exc}"
) from exc
except (TypeError, ValueError) as exc:
raise PluginConfigLoadError(
f"Invalid plugin configuration file {config_path}: the file must "
"contain a mapping of setting names to values"
) from exc
class MVTPluginSettings(BaseSettings):
"""
Base class for plugin-namespaced settings.
Subclass with typed fields and set `plugin_name`. Values resolve from
constructor arguments, then environment variables (MVT_PLUGIN_<NAME>_*),
then the plugin's YAML file (~/.config/mvt/plugins/<name>.yaml), then field
defaults.
Plugins must not store their settings in MVT's own configuration file: MVT
rewrites it with the fields it knows about, dropping anything else.
`data_folder()` returns the folder the plugin keeps its data in.
"""
model_config = SettingsConfigDict(extra="ignore")
plugin_name: ClassVar[str]
def __init_subclass__(cls, **kwargs: Any) -> None:
super().__init_subclass__(**kwargs)
plugin_name = _settings_plugin_name(cls)
# Namespace the environment variables of this plugin. Each pydantic
# model gets its own configuration dictionary, so this does not leak
# into other plugins.
cls.model_config["env_prefix"] = plugin_env_prefix(plugin_name)
@classmethod
def settings_customise_sources(
cls,
settings_cls: Type[BaseSettings],
init_settings: PydanticBaseSettingsSource,
env_settings: PydanticBaseSettingsSource,
dotenv_settings: PydanticBaseSettingsSource,
file_secret_settings: PydanticBaseSettingsSource,
) -> Tuple[PydanticBaseSettingsSource, ...]:
config_path = plugin_config_path(_settings_plugin_name(settings_cls))
yaml_source = _plugin_yaml_source(settings_cls, config_path)
# Explicit arguments take precedence over environment variables, which
# in turn take precedence over the configuration file.
return (init_settings, env_settings, yaml_source)
@classmethod
def load(cls: Type[PluginSettingsType]) -> PluginSettingsType:
"""
Load the settings of the plugin.
A missing configuration file is not an error: the settings then come
from the environment and from the field defaults.
"""
return cls()
@classmethod
def data_folder(cls) -> str:
"""
Return the data folder of the plugin, creating it.
The folder is the one plugin_data_folder() returns for `plugin_name`,
so a plugin with a settings class does not repeat its name.
"""
return plugin_data_folder(_settings_plugin_name(cls))
def _environment_values(self) -> Dict[str, Any]:
"""
Return the settings values currently supplied by the environment.
Values are validated by the model, so they can be compared with the
values held by this instance.
"""
settings_cls = type(self)
raw_values = EnvSettingsSource(settings_cls)()
names = [name for name in raw_values if name in settings_cls.model_fields]
if not names:
return {}
# Fall back on the current values for the fields the environment does
# not set, so that required fields do not fail validation here.
current_values = json.loads(self.model_dump_json())
try:
from_environment = settings_cls.model_validate(
{**current_values, **raw_values}
)
except ValidationError:
# An environment variable which the model cannot validate must not
# stop the other environment values from being recognised, or a
# credential would be written to the configuration file.
return self._environment_values_by_field(current_values, raw_values, names)
return {name: getattr(from_environment, name) for name in names}
def _environment_values_by_field(
self,
current_values: Dict[str, Any],
raw_values: Dict[str, Any],
names: List[str],
) -> Dict[str, Any]:
"""
Validate each environment value on its own, skipping unusable ones.
:param current_values: Serialized values held by this instance.
:param raw_values: Values supplied by the environment.
:param names: Names of the fields set by the environment.
"""
settings_cls = type(self)
values = {}
for name in names:
try:
from_environment = settings_cls.model_validate(
{**current_values, name: raw_values[name]}
)
except ValidationError:
continue
values[name] = getattr(from_environment, name)
return values
def save(self) -> None:
"""
Save the current settings to the configuration file of the plugin.
Only values which differ from the field defaults are persisted. Values
which come from the environment are not written to disk, so credentials
passed as environment variables stay out of the configuration file.
MVT's own configuration file is never modified.
"""
config_folder = plugin_config_folder()
if not os.path.isdir(config_folder):
os.makedirs(config_folder, mode=0o700, exist_ok=True)
values = json.loads(self.model_dump_json(exclude_defaults=True))
for name, environment_value in self._environment_values().items():
if name in values and getattr(self, name, None) == environment_value:
del values[name]
# Settings files can hold credentials, so write them through a private
# temporary file and move it in place. The file is then never partially
# written and never briefly readable by other users.
config_path = plugin_config_path(self.plugin_name)
descriptor, temporary_path = tempfile.mkstemp(
dir=config_folder, prefix=f".{self.plugin_name}-", suffix=".yaml"
)
try:
with os.fdopen(descriptor, "w") as config_file:
config_file.write(yaml.dump(values, default_flow_style=False))
os.replace(temporary_path, config_path)
except BaseException:
with contextlib.suppress(OSError):
os.unlink(temporary_path)
raise
+3 -416
View File
@@ -3,13 +3,8 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import importlib.metadata
import json
import logging
import os
import re
import shlex
import subprocess
from datetime import datetime
from typing import Optional, Tuple
@@ -17,35 +12,14 @@ import requests
import yaml
from packaging import version
from .cli_plugins import (
ANDROID_CLI_PLUGIN_GROUP,
IOS_CLI_PLUGIN_GROUP,
NEUTRAL_CLI_PLUGIN_GROUP,
)
from .config import settings
from .indicators import MVT_DATA_FOLDER, MVT_INDICATORS_FOLDER
from .module_loader import MODULES_ENTRY_POINT_GROUP, distribution_direct_url
from .version import MVT_VERSION
log = logging.getLogger(__name__)
# In hours.
INDICATORS_CHECK_FREQUENCY = 12
PLUGINS_CHECK_FREQUENCY = 12
# The entry-point groups a package can use to extend MVT.
PLUGIN_ENTRY_POINT_GROUPS = (
MODULES_ENTRY_POINT_GROUP,
IOS_CLI_PLUGIN_GROUP,
ANDROID_CLI_PLUGIN_GROUP,
NEUTRAL_CLI_PLUGIN_GROUP,
)
SHORT_COMMIT_LENGTH = 8
# The keys every cached finding has to carry to be printed.
FINDING_KEYS = ("name", "installed", "latest", "upgrade_command")
# Options which stop ssh from waiting for an answer nobody is there to give.
_SSH_BATCH_OPTIONS = ("-o", "BatchMode=yes", "-o", "ConnectTimeout=10")
_COMMIT_PATTERN = re.compile(r"\A[0-9a-f]{7,40}\Z")
class MVTUpdates:
@@ -64,395 +38,6 @@ class MVTUpdates:
return ""
def installed_plugin_distributions() -> list[importlib.metadata.Distribution]:
"""Return the installed distributions which extend MVT.
A plugin package is any distribution registering at least one entry point
in the module or CLI command groups. Distributions are returned once each,
sorted by name. MVT itself is not a plugin and is never returned.
"""
distributions: dict[str, importlib.metadata.Distribution] = {}
for group in PLUGIN_ENTRY_POINT_GROUPS:
try:
entry_points = importlib.metadata.entry_points(group=group)
except Exception as exc:
log.warning(
"Unable to discover installed plugin packages in entry-point "
"group %s: %s",
group,
exc,
)
continue
for entry_point in entry_points:
# Manually constructed entry points have no associated distribution.
dist = getattr(entry_point, "dist", None)
if dist is None:
continue
try:
name = dist.name
except Exception:
continue
if not name or name == "mvt":
continue
distributions.setdefault(name, dist)
return [distributions[name] for name in sorted(distributions)]
def _is_usable_finding(finding: object) -> bool:
"""Check that a cached finding carries everything needed to print it."""
if not isinstance(finding, dict):
return False
return all(
isinstance(finding.get(key), str) and finding.get(key) for key in FINDING_KEYS
)
def _installed_revision(
dist: importlib.metadata.Distribution, origin: object
) -> Optional[str]:
"""Return what a plugin's installed revision is right now.
This is the value a finding recorded as installed when it was made, so a
finding can be compared against the current state of the installation
without looking anything up remotely.
"""
try:
if origin != "git":
return dist.version
vcs_info = (distribution_direct_url(dist) or {}).get("vcs_info")
if not isinstance(vcs_info, dict):
return None
commit = vcs_info.get("commit_id") or ""
return commit[:SHORT_COMMIT_LENGTH] or None
except Exception as e:
log.debug("Failed to read the installed revision of a plugin: %s", e)
return None
def _batch_mode_ssh_command(ssh_command: str) -> str:
"""Return an ssh command line which cannot stop to ask a question.
ssh keeps the first value it is given for a keyword, so the batch mode
options are inserted right after the ssh program, ahead of whatever the
analyst configured. Their remaining options, such as which key to use,
still apply.
"""
try:
arguments = shlex.split(ssh_command.strip())
except ValueError:
arguments = []
if not arguments:
arguments = ["ssh"]
return shlex.join([arguments[0], *_SSH_BATCH_OPTIONS, *arguments[1:]])
def _revision_pins_commit(revision: str, commit: str) -> bool:
"""Check whether a requested revision pins the installed commit."""
candidate = revision.lower()
if not _COMMIT_PATTERN.match(candidate):
return False
return commit.lower().startswith(candidate)
class PluginUpdates:
"""Check for updates to the installed MVT plugin packages.
MVT never installs or upgrades a plugin package itself. It only reports
the command which upgrades a plugin, leaving the analyst to decide when to
run it.
"""
@property
def latest_check_path(self) -> str:
return os.path.join(MVT_DATA_FOLDER, "latest_plugins_check")
@property
def findings_path(self) -> str:
return os.path.join(MVT_DATA_FOLDER, "plugin_updates.json")
def _create_data_folder(self) -> None:
if not os.path.exists(MVT_DATA_FOLDER):
os.makedirs(MVT_DATA_FOLDER)
def get_latest_check(self) -> int:
if not os.path.exists(self.latest_check_path):
return 0
# A corrupt or truncated timestamp only means the next check happens
# sooner. It must never stop MVT from running.
try:
with open(self.latest_check_path, "r", encoding="utf-8") as handle:
data = handle.read().strip()
if data:
return int(data)
except (OSError, ValueError) as e:
log.debug("Failed to read the time of the latest plugin check: %s", e)
return 0
def set_latest_check(self) -> None:
self._create_data_folder()
timestamp = int(datetime.now().timestamp())
with open(self.latest_check_path, "w", encoding="utf-8") as handle:
handle.write(str(timestamp))
def get_findings(self) -> list[dict]:
"""
Return the findings of the latest check, without checking again.
Returns an empty list if no check was ever performed.
"""
if not os.path.exists(self.findings_path):
return []
try:
with open(self.findings_path, "r", encoding="utf-8") as handle:
findings = json.load(handle)
except Exception as e:
log.debug("Failed to read the cached plugin updates: %s", e)
return []
if not isinstance(findings, list):
return []
# Anything which does not look like a finding is dropped rather than
# trusted: the cache is only a convenience.
return [finding for finding in findings if _is_usable_finding(finding)]
def current_findings(
self, distributions: Optional[list[importlib.metadata.Distribution]] = None
) -> list[dict]:
"""
Return the cached findings which still apply to what is installed.
Findings about a plugin which was upgraded or removed since the latest
check are dropped, so an update is never reported twice.
"""
if distributions is None:
distributions = installed_plugin_distributions()
installed = {}
for dist in distributions:
try:
installed[dist.name] = dist
except Exception:
continue
current = []
for finding in self.get_findings():
plugin = installed.get(finding["name"])
if plugin is None:
continue
if (
_installed_revision(plugin, finding.get("origin"))
!= finding["installed"]
):
continue
current.append(finding)
return current
def set_findings(self, findings: list[dict]) -> None:
self._create_data_folder()
with open(self.findings_path, "w", encoding="utf-8") as handle:
json.dump(findings, handle)
def should_check(self) -> Tuple[bool, int]:
"""
Compare time of the latest plugins check with current time.
Returns bool and number of hours since the last check.
"""
now = datetime.now()
latest_check_ts = self.get_latest_check()
latest_check_dt = datetime.fromtimestamp(latest_check_ts)
diff = now - latest_check_dt
diff_hours = divmod(diff.total_seconds(), 3600)[0]
if diff_hours >= PLUGINS_CHECK_FREQUENCY:
return True, 0
return False, int(PLUGINS_CHECK_FREQUENCY - diff_hours)
def _check_index_plugin(self, name: str, installed: str) -> Optional[dict]:
"""Check a plugin installed from a package index for a newer release."""
url = f"https://pypi.org/pypi/{name}/json"
try:
res = requests.get(url, timeout=settings.NETWORK_TIMEOUT)
except requests.exceptions.RequestException as e:
log.debug("Failed to check for updates to plugin %s: %s", name, e)
return None
# Plugins which were never published to a public index are expected,
# and there is nothing to compare their version against.
if res.status_code == 404:
return None
if res.status_code != 200:
log.debug(
"Failed to check for updates to plugin %s (error %d)",
name,
res.status_code,
)
return None
try:
latest = res.json().get("info", {}).get("version", "")
if not latest or version.parse(latest) <= version.parse(installed):
return None
except Exception as e:
log.debug("Failed to compare the versions of plugin %s: %s", name, e)
return None
return {
"name": name,
"installed": installed,
"latest": latest,
"origin": "pypi",
# The name comes from package metadata, so the command MVT
# suggests is quoted rather than assumed to be shell-safe.
"upgrade_command": f"pip install -U {shlex.quote(name)}",
}
def _git_ls_remote(self, url: str, revision: str) -> list[Tuple[str, str]]:
"""Return the remote references matching a revision, if git allows it."""
# Neither value is trusted: they are read from the metadata of an
# installed package and must not turn into git options.
if url.startswith("-") or revision.startswith("-"):
log.debug("Skipping the update check for the invalid repository %s", url)
return []
environment = dict(os.environ)
# Never prompt the analyst for repository credentials. git handles its
# own prompts, while ssh reads the terminal directly and only batch
# mode makes it fail instead of asking.
environment["GIT_TERMINAL_PROMPT"] = "0"
environment["GIT_SSH_COMMAND"] = _batch_mode_ssh_command(
environment.get("GIT_SSH_COMMAND", "")
)
try:
process = subprocess.run(
["git", "ls-remote", url, revision],
capture_output=True,
stdin=subprocess.DEVNULL,
text=True,
env=environment,
timeout=settings.NETWORK_TIMEOUT,
check=False,
)
except FileNotFoundError:
log.debug("Could not find git, skipping the update check for %s", url)
return []
except (subprocess.SubprocessError, OSError) as e:
log.debug("Failed to query the repository %s: %s", url, e)
return []
if process.returncode != 0:
log.debug(
"Failed to query the repository %s (error %d): %s",
url,
process.returncode,
(process.stderr or "").strip(),
)
return []
references = []
for line in (process.stdout or "").splitlines():
commit, _, reference = line.partition("\t")
if commit.strip() and reference.strip():
references.append((commit.strip(), reference.strip()))
return references
def _check_repository_plugin(
self, name: str, direct_url: dict, vcs_info: dict
) -> Optional[dict]:
"""Check a plugin installed from a repository for a newer commit."""
url = direct_url.get("url") or ""
installed = vcs_info.get("commit_id") or ""
revision = vcs_info.get("requested_revision") or ""
if not url or not installed:
return None
# A plugin installed from a commit is pinned and never goes out of
# date, no matter what the branch it came from does next.
if revision and _revision_pins_commit(revision, installed):
return None
latest = ""
wanted_reference = f"refs/heads/{revision}" if revision else "HEAD"
for commit, reference in self._git_ls_remote(url, revision or "HEAD"):
# Tags are pinned installs too.
if reference.startswith("refs/tags/"):
return None
if reference == wanted_reference:
latest = commit
if not latest or latest == installed:
return None
requirement = f"{name} @ git+{url}"
if revision:
requirement += f"@{revision}"
return {
"name": name,
"installed": installed[:SHORT_COMMIT_LENGTH],
"latest": latest[:SHORT_COMMIT_LENGTH],
"origin": "git",
# A repository URL and a branch name can both hold characters a
# shell would act on, so the requirement is quoted for the shell
# the analyst is going to paste the command into.
"upgrade_command": f"pip install -U {shlex.quote(requirement)}",
}
def _check_distribution(
self, dist: importlib.metadata.Distribution
) -> Optional[dict]:
try:
name = dist.name
installed = dist.version
except Exception as e:
log.debug("Failed to read the metadata of an installed plugin: %s", e)
return None
direct_url = distribution_direct_url(dist)
if direct_url is None:
return self._check_index_plugin(name, installed)
vcs_info = direct_url.get("vcs_info")
if isinstance(vcs_info, dict):
return self._check_repository_plugin(name, direct_url, vcs_info)
# Plugins installed from a local folder, including editable installs,
# are maintained by the analyst and have nothing to check against.
return None
def check(self) -> list[dict]:
"""
Check every installed plugin package for an available update.
Returns one entry per plugin which can be upgraded.
"""
findings = []
for dist in installed_plugin_distributions():
finding = self._check_distribution(dist)
if finding:
findings.append(finding)
self.set_findings(findings)
self.set_latest_check()
return findings
class IndicatorsUpdates:
def __init__(self) -> None:
self.github_raw_url = "https://raw.githubusercontent.com/{}/{}/{}/{}"
@@ -595,7 +180,9 @@ class IndicatorsUpdates:
def _get_remote_file_latest_commit(
self, owner: str, repo: str, branch: str, path: str
) -> int:
file_commit_url = f"https://api.github.com/repos/{owner}/{repo}/commits?path={path}&sha={branch}"
file_commit_url = (
f"https://api.github.com/repos/{owner}/{repo}/commits?path={path}&sha={branch}"
)
try:
res = requests.get(file_commit_url, timeout=5)
except requests.exceptions.RequestException as e:
+1 -3
View File
@@ -349,9 +349,7 @@ class URL:
return tld_obj
if tld_obj is None:
return ""
# removeprefix, not lstrip: lstrip takes a set of characters, so it ate the
# leading "w"s and dots of any domain ("web.evil.com" -> "eb.evil.com").
return tld_obj.parsed_url.netloc.lower().removeprefix("www.")
return tld_obj.parsed_url.netloc.lower().lstrip("www.")
def get_top_level(self) -> str:
"""Get only the top-level domain from a URL.
+6 -22
View File
@@ -14,6 +14,7 @@ from dataclasses import asdict, is_dataclass
from typing import Any, Iterator, Union
from .log import MVTLogHandler
from mvt.common.config import settings
class CustomJSONEncoder(json.JSONEncoder):
@@ -238,13 +239,6 @@ def init_logging(verbose: bool = False):
"""
log = logging.getLogger("mvt")
log.setLevel(logging.DEBUG)
# Importing an MVT CLI module calls init_logging() at import time, and
# loaded module packages may import one indirectly. Keep this idempotent
# so console log lines are not duplicated by a second handler.
if any(isinstance(handler, MVTLogHandler) for handler in log.handlers):
return
consoleHandler = MVTLogHandler()
consoleHandler.setFormatter(logging.Formatter("%(message)s"))
if verbose:
@@ -255,26 +249,16 @@ def init_logging(verbose: bool = False):
def set_verbose_logging(verbose: bool = False):
"""Raise or lower the verbosity of MVT's console output.
Only MVT's own console handler is adjusted, wherever it sits in the list.
The file handler a command attaches to its output folder keeps recording
everything, so the command.log of a run does not depend on how the run was
invoked, and a handler attached to the "mvt" logger by anything else is
left alone.
"""
log = logging.getLogger("mvt")
for handler in log.handlers:
if isinstance(handler, MVTLogHandler):
handler.setLevel(logging.DEBUG if verbose else logging.INFO)
handler = log.handlers[0]
if verbose:
handler.setLevel(logging.DEBUG)
else:
handler.setLevel(logging.INFO)
def exec_or_profile(module, globals, locals):
"""Hook for profiling MVT modules"""
# Imported here so that the CLI modules, which import this one at start-up,
# do not load the settings (and pydantic) before a command runs.
from .config import settings
if settings.PROFILE:
cProfile.runctx(module, globals, locals)
else:
+1 -3
View File
@@ -3,6 +3,4 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from importlib.metadata import version
MVT_VERSION = version("mvt")
MVT_VERSION = "2026.6.29"
+1 -1
View File
@@ -3,4 +3,4 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from .cli import cli, main
from .cli import cli
+77 -94
View File
@@ -8,13 +8,16 @@ import logging
import os
import click
from mvt.common.cli_plugins import (
IOS_CLI_PLUGIN_GROUP,
MVT_IOS_CUSTOM_COMMANDS_ENV,
load_cli_commands_option,
register_cli_plugins,
from mvt.common.cmd_check_iocs import CmdCheckIOCS
from mvt.common.completion import (
SUPPORTED_SHELLS,
completion_instructions,
generate_completion_script,
install_completion_script,
)
from mvt.common.logo import logo
from mvt.common.options import MutuallyExclusiveOption
from mvt.common.updates import IndicatorsUpdates
from mvt.common.utils import (
generate_hashes_from_path,
init_logging,
@@ -24,7 +27,6 @@ from mvt.common.help import (
HELP_MSG_VERSION,
HELP_MSG_DECRYPT_BACKUP,
HELP_MSG_BACKUP_DESTINATION,
HELP_MSG_DECRYPT_JOBS,
HELP_MSG_IOS_BACKUP_PASSWORD,
HELP_MSG_BACKUP_KEYFILE,
HELP_MSG_HASHES,
@@ -36,7 +38,6 @@ from mvt.common.help import (
HELP_MSG_LOAD_MODULE,
HELP_MSG_MODULE,
HELP_MSG_VERBOSE,
HELP_MSG_VERBOSE_COMMAND,
HELP_MSG_CHECK_FS,
HELP_MSG_CHECK_IOCS,
HELP_MSG_STIX2,
@@ -44,17 +45,17 @@ from mvt.common.help import (
HELP_MSG_CHECK_SYSDIAGNOSE,
HELP_MSG_DISABLE_UPDATE_CHECK,
HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
HELP_MSG_COMPLETION,
)
from mvt.common.module_loader import CustomModuleLoadError, load_custom_modules
from mvt.common.password import prompt_password
from .decrypt_config import (
DEFAULT_DECRYPT_WORKERS,
MAX_DECRYPT_WORKERS,
)
# The commands import what they run only when they are invoked. This module is
# imported at every start of mvt-ios, including by shell completion on every
# keystroke, so importing it must do no more than build the command tree: the
# forensic modules, the backup decryption and the update checks stay out of it.
from .cmd_check_backup import CmdIOSCheckBackup
from .cmd_check_fs import CmdIOSCheckFS
from .cmd_check_sysdiagnose import CmdIOSCheckSysdiagnose
from .decrypt import DecryptBackup
from .modules.backup import BACKUP_MODULES
from .modules.fs import FS_MODULES
from .modules.mixed import MIXED_MODULES
init_logging()
log = logging.getLogger("mvt")
@@ -74,14 +75,7 @@ def _get_disable_flags(ctx):
)
def _get_verbose(ctx):
"""Return whether --verbose was passed to the CLI itself."""
return bool(ctx.obj and ctx.obj.get("verbose", False))
def _load_custom_modules(load_module):
from mvt.common.module_loader import CustomModuleLoadError, load_custom_modules
try:
return load_custom_modules(load_module)
except CustomModuleLoadError as exc:
@@ -92,7 +86,6 @@ def _load_custom_modules(load_module):
# Main
# ==============================================================================
@click.group(invoke_without_command=False)
@load_cli_commands_option
@click.option(
"--disable-update-check", is_flag=True, help=HELP_MSG_DISABLE_UPDATE_CHECK
)
@@ -101,31 +94,60 @@ def _load_custom_modules(load_module):
is_flag=True,
help=HELP_MSG_DISABLE_INDICATOR_UPDATE_CHECK,
)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.pass_context
def cli(ctx, disable_update_check, disable_indicator_update_check, verbose):
def cli(ctx, disable_update_check, disable_indicator_update_check):
ctx.ensure_object(dict)
ctx.obj["disable_version_check"] = disable_update_check
ctx.obj["disable_indicator_check"] = disable_indicator_update_check
ctx.obj["verbose"] = verbose
set_verbose_logging(verbose)
from mvt.common.logo import logo
logo(
disable_version_check=disable_update_check,
disable_indicator_check=disable_indicator_update_check,
)
if ctx.invoked_subcommand != "completion":
logo(
disable_version_check=disable_update_check,
disable_indicator_check=disable_indicator_update_check,
)
# ==============================================================================
# Command: version
# ==============================================================================
@cli.command("version", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_VERSION)
@cli.command("version", help=HELP_MSG_VERSION)
def version():
return
# ==============================================================================
# Command: completion
# ==============================================================================
@cli.command("completion", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_COMPLETION)
@click.argument("shell", required=False, type=click.Choice(SUPPORTED_SHELLS))
@click.option(
"--install",
is_flag=True,
help="Write completion files and update shell configuration.",
)
@click.pass_context
def completion(ctx, shell, install):
program_name = "mvt-ios"
if shell is None:
if install:
raise click.UsageError("A shell is required when using --install.")
click.echo(completion_instructions(program_name))
return
root_cli = ctx.find_root().command
if install:
script_path = install_completion_script(root_cli, program_name, shell)
click.echo(f"Installed {shell} completion to {script_path}")
if shell in ("bash", "zsh"):
click.echo(f"Updated ~/.{shell}rc")
else:
click.echo("Fish loads completion files automatically.")
return
click.echo(generate_completion_script(root_cli, program_name, shell))
# ==============================================================================
# Command: decrypt-backup
# ==============================================================================
@@ -133,13 +155,6 @@ def version():
"decrypt-backup", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_DECRYPT_BACKUP
)
@click.option("--destination", "-d", required=True, help=HELP_MSG_BACKUP_DESTINATION)
@click.option(
"--jobs",
type=click.IntRange(1, MAX_DECRYPT_WORKERS),
default=DEFAULT_DECRYPT_WORKERS,
show_default=True,
help=HELP_MSG_DECRYPT_JOBS,
)
@click.option(
"--password",
"-p",
@@ -158,10 +173,8 @@ def version():
@click.option("--hashes", "-H", is_flag=True, help=HELP_MSG_HASHES)
@click.argument("BACKUP_PATH", type=click.Path(exists=True))
@click.pass_context
def decrypt_backup(ctx, destination, jobs, password, key_file, hashes, backup_path):
from .decrypt import DecryptBackup
backup = DecryptBackup(backup_path, destination, max_workers=jobs)
def decrypt_backup(ctx, destination, password, key_file, hashes, backup_path):
backup = DecryptBackup(backup_path, destination)
if key_file:
if MVT_IOS_BACKUP_PASSWORD in os.environ:
@@ -224,8 +237,6 @@ def decrypt_backup(ctx, destination, jobs, password, key_file, hashes, backup_pa
)
@click.argument("BACKUP_PATH", type=click.Path(exists=True))
def extract_key(password, key_file, backup_path):
from .decrypt import DecryptBackup
backup = DecryptBackup(backup_path)
if password:
@@ -278,7 +289,7 @@ def extract_key(password, key_file, backup_path):
help=HELP_MSG_LOAD_MODULE,
)
@click.option("--hashes", "-H", is_flag=True, help=HELP_MSG_HASHES)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("BACKUP_PATH", type=click.Path(exists=True))
@click.pass_context
def check_backup(
@@ -293,9 +304,7 @@ def check_backup(
verbose,
backup_path,
):
from .cmd_check_backup import CmdIOSCheckBackup
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
module_options = {"fast_mode": fast}
custom_modules = _load_custom_modules(load_module)
@@ -318,6 +327,8 @@ def check_backup(
if not cmd.resolve_backup_path():
ctx.exit(1)
log.info("Checking iTunes backup located at: %s", cmd.target_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_support_message()
@@ -347,7 +358,7 @@ def check_backup(
help=HELP_MSG_LOAD_MODULE,
)
@click.option("--hashes", "-H", is_flag=True, help=HELP_MSG_HASHES)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("DUMP_PATH", type=click.Path(exists=True))
@click.pass_context
def check_fs(
@@ -362,9 +373,7 @@ def check_fs(
verbose,
dump_path,
):
from .cmd_check_fs import CmdIOSCheckFS
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
module_options = {"fast_mode": fast}
custom_modules = _load_custom_modules(load_module)
@@ -384,6 +393,8 @@ def check_fs(
cmd.list_modules()
return
log.info("Checking iOS filesystem located at: %s", dump_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_support_message()
@@ -416,7 +427,7 @@ def check_fs(
help=HELP_MSG_LOAD_MODULE,
)
@click.option("--hashes", "-H", is_flag=True, help=HELP_MSG_HASHES)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE_COMMAND)
@click.option("--verbose", "-v", is_flag=True, help=HELP_MSG_VERBOSE)
@click.argument("SYSDIAGNOSE_PATH", type=click.Path(exists=True))
@click.pass_context
def check_sysdiagnose(
@@ -430,9 +441,7 @@ def check_sysdiagnose(
verbose,
sysdiagnose_path,
):
from .cmd_check_sysdiagnose import CmdIOSCheckSysdiagnose
set_verbose_logging(verbose or _get_verbose(ctx))
set_verbose_logging(verbose)
custom_modules = _load_custom_modules(load_module)
cmd = CmdIOSCheckSysdiagnose(
target_path=sysdiagnose_path,
@@ -445,20 +454,18 @@ def check_sysdiagnose(
custom_modules=custom_modules,
)
# MVT's own module only records the device details; the checks come from
# custom modules, so a run without any must not look like a clean analysis.
if all(module in cmd.modules for module in cmd._available_modules()):
log.warning(
"No forensic sysdiagnose modules have been loaded: MVT's own "
"SysdiagnoseInfo module only records the device details. Install a "
"module package or load a module that declares supported_commands = "
'(("ios", "check-sysdiagnose"),) to check the sysdiagnose.'
if not cmd._available_modules():
raise click.ClickException(
"No custom modules support mvt-ios check-sysdiagnose. "
"Load a module that declares supported_commands = "
"((\"ios\", \"check-sysdiagnose\"),)."
)
if list_modules:
cmd.list_modules()
return
log.info("Checking iOS sysdiagnose at path: %s", sysdiagnose_path)
cmd.run()
cmd.show_alerts_brief()
cmd.show_support_message()
@@ -488,10 +495,6 @@ def check_sysdiagnose(
@click.argument("FOLDER", type=click.Path(exists=True))
@click.pass_context
def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
from mvt.common.cmd_check_iocs import CmdCheckIOCS
from .command_modules import IOS_CHECK_IOCS_MODULES
custom_modules = _load_custom_modules(load_module)
cmd = CmdCheckIOCS(
target_path=folder,
@@ -502,7 +505,7 @@ def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
custom_modules=custom_modules,
platform="ios",
)
cmd.modules = IOS_CHECK_IOCS_MODULES
cmd.modules = BACKUP_MODULES + FS_MODULES + MIXED_MODULES
if list_modules:
cmd.list_modules()
@@ -518,25 +521,5 @@ def check_iocs(ctx, iocs, list_modules, module, load_module, folder):
# ==============================================================================
@cli.command("download-iocs", context_settings=CONTEXT_SETTINGS, help=HELP_MSG_STIX2)
def download_iocs():
from mvt.common.updates import IndicatorsUpdates
ioc_updates = IndicatorsUpdates()
ioc_updates.update()
# ==============================================================================
# Entry point of the mvt-ios console script
# ==============================================================================
def main() -> None:
"""Register the external commands and run the mvt-ios CLI.
External commands are registered here rather than when this module is
imported, so that importing MVT never runs third-party code and a plugin
importing from MVT cannot re-enter a module that is still initializing.
"""
register_cli_plugins(
cli,
entry_point_group=IOS_CLI_PLUGIN_GROUP,
environment_variable=MVT_IOS_CUSTOM_COMMANDS_ENV,
)
cli()
-3
View File
@@ -59,9 +59,6 @@ class CmdIOSCheckBackup(Command):
self.name = "check-backup"
self.modules = BACKUP_MODULES + MIXED_MODULES
def init(self) -> None:
self.log.info("Checking iTunes backup located at: %s", self.target_path)
def resolve_backup_path(self) -> bool:
target_path = getattr(self, "target_path", None)
if not isinstance(target_path, str) or not target_path:
-3
View File
@@ -51,8 +51,5 @@ class CmdIOSCheckFS(Command):
self.name = "check-fs"
self.modules = FS_MODULES + MIXED_MODULES
def init(self) -> None:
self.log.info("Checking iOS filesystem located at: %s", self.target_path)
def module_init(self, module):
module.is_fs_dump = True
+13 -92
View File
@@ -6,20 +6,14 @@
import json
import logging
import os
import shutil
import sys
import tarfile
import zlib
from pathlib import Path, PurePosixPath
from tempfile import TemporaryDirectory
from pathlib import Path
from typing import Any, Optional
from mvt.common.command import Command
from mvt.common.indicators import Indicators
from mvt.common.module import MVTModule
from .modules.sysdiagnose import SYSDIAGNOSE_MODULES
log = logging.getLogger(__name__)
@@ -56,13 +50,10 @@ class CmdIOSCheckSysdiagnose(Command):
)
self.platform = "ios"
self.name = "check-sysdiagnose"
self.modules = SYSDIAGNOSE_MODULES
self.sysdiagnose_format: Optional[str] = None
self.sysdiagnose_archive: Optional[tarfile.TarFile] = None
self.sysdiagnose_files: list[str] = []
self.ips_files: list[dict[str, Any]] = []
self.temp_sysdiagnose_dir: Optional[TemporaryDirectory[str]] = None
self.extracted_sysdiagnose_path: Optional[str] = None
@staticmethod
def _parse_bugtype_header(data: bytes) -> Optional[int]:
@@ -81,15 +72,11 @@ class CmdIOSCheckSysdiagnose(Command):
if not self.target_path:
raise ValueError("A sysdiagnose path is required")
self.log.info("Checking iOS sysdiagnose at path: %s", self.target_path)
if os.path.isdir(self.target_path):
self.sysdiagnose_format = "dir"
parent_path = Path(self.target_path).absolute().parent
for root, _, filenames in os.walk(self.target_path):
for filename in filenames:
if filename.startswith("._"):
continue
absolute_path = os.path.join(root, filename)
file_path = os.path.relpath(absolute_path, parent_path)
self.sysdiagnose_files.append(file_path)
@@ -103,85 +90,22 @@ class CmdIOSCheckSysdiagnose(Command):
self.log.info("Parsing sysdiagnose archive. This might take a while...")
self.sysdiagnose_format = "tar"
try:
self.sysdiagnose_archive = tarfile.open(self.target_path, "r:gz")
self._extract_sysdiagnose_archive()
except (tarfile.ReadError, EOFError, zlib.error, OSError) as exc:
# A truncated archive ends in EOFError from gzip, which Click would
# otherwise report as a bare "Aborted!" with no reason.
self.log.critical(
"Unable to read the sysdiagnose archive %s: %s. "
"The file may be truncated or not a gzip-compressed tarball.",
self.target_path,
exc,
)
sys.exit(1)
def _extract_sysdiagnose_archive(self) -> None:
archive = self.sysdiagnose_archive
if archive is None:
raise RuntimeError("Sysdiagnose archive has not been initialized")
self.temp_sysdiagnose_dir = TemporaryDirectory()
extraction_root = Path(self.temp_sysdiagnose_dir.name).resolve()
archive_roots = set()
for member in archive:
member_path = PurePosixPath(member.name.replace("\\", "/"))
if member_path.is_absolute() or ".." in member_path.parts:
self.log.warning("Skipping unsafe sysdiagnose path %r", member.name)
continue
destination = extraction_root.joinpath(*member_path.parts).resolve()
if not destination.is_relative_to(extraction_root):
self.log.warning("Skipping unsafe sysdiagnose path %r", member.name)
continue
if not member_path.parts:
continue
# AppleDouble sidecars (._name) carry a file's extended attributes,
# not sysdiagnose content. Device archives hold hundreds of them;
# bsdtar hides them from listings, tarfile does not.
if member_path.name.startswith("._"):
continue
archive_roots.add(member_path.parts[0])
if member.isdir():
destination.mkdir(parents=True, exist_ok=True)
continue
# Modules only need directories and regular files. Do not materialize
# links or device nodes from an untrusted sysdiagnose archive.
if not member.isfile():
self.log.warning("Skipping unsafe sysdiagnose member %r", member.name)
continue
normalized_name = member_path.as_posix()
self.sysdiagnose_files.append(normalized_name)
source = archive.extractfile(member)
if source is None:
continue
destination.parent.mkdir(parents=True, exist_ok=True)
with source, destination.open("wb") as output:
shutil.copyfileobj(source, output)
if normalized_name.endswith(".ips"):
self._add_ips_file(str(destination), destination.read_bytes())
if len(archive_roots) != 1:
raise ValueError("Sysdiagnose archive must contain one top-level directory")
self.extracted_sysdiagnose_path = str(extraction_root / archive_roots.pop())
self.sysdiagnose_archive = tarfile.open(self.target_path, "r:gz")
for member in self.sysdiagnose_archive:
self.sysdiagnose_files.append(member.name)
if member.isfile() and member.name.endswith(".ips"):
archive_handle = self.sysdiagnose_archive.extractfile(member)
if archive_handle is not None:
with archive_handle:
self._add_ips_file(member.name, archive_handle.read())
def module_init(self, module) -> None:
module.ips_files = self.ips_files
if self.sysdiagnose_format == "tar":
if self.extracted_sysdiagnose_path is None:
raise RuntimeError("Sysdiagnose archive has not been extracted")
module.from_sysdiagnose_folder(
self.extracted_sysdiagnose_path, self.sysdiagnose_files
if self.sysdiagnose_archive is None:
raise RuntimeError("Sysdiagnose archive has not been initialized")
module.from_sysdiagnose_tar(
self.sysdiagnose_archive, self.sysdiagnose_files
)
return
if self.sysdiagnose_format == "dir" and self.target_path:
@@ -193,6 +117,3 @@ class CmdIOSCheckSysdiagnose(Command):
if self.sysdiagnose_archive is not None:
self.sysdiagnose_archive.close()
self.sysdiagnose_archive = None
if self.temp_sysdiagnose_dir is not None:
self.temp_sysdiagnose_dir.cleanup()
self.temp_sysdiagnose_dir = None
-23
View File
@@ -1,23 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
"""Module lists an mvt-ios command composes from more than one family.
Commands whose modules are one family read that family directly. check-iocs
re-checks stored results, so it has to know every module that could have
written one, and both the CLI and any other code needing that answer share
the list from here rather than each concatenating their own.
"""
from mvt.common.module import MVTModule
from .modules.backup import BACKUP_MODULES
from .modules.fs import FS_MODULES
from .modules.mixed import MIXED_MODULES
from .modules.sysdiagnose import SYSDIAGNOSE_MODULES
IOS_CHECK_IOCS_MODULES: list[type[MVTModule]] = (
BACKUP_MODULES + FS_MODULES + MIXED_MODULES + SYSDIAGNOSE_MODULES
)
-24
View File
@@ -1216,14 +1216,6 @@
"version": "18.7.9",
"build": "22H355"
},
{
"version": "18.7.10",
"build": "22H373"
},
{
"version": "18.7.10",
"build": "22H374"
},
{
"version": "26",
"build": "23A341"
@@ -1263,21 +1255,5 @@
{
"version": "26.5",
"build": "23F77"
},
{
"version": "26.6.1",
"build": "23G82"
},
{
"version": "26.6.1",
"build": "23G83"
},
{
"version": "26.6.2",
"build": "23G90"
},
{
"version": "27.0",
"build": "24A437"
}
]
+74 -292
View File
@@ -6,179 +6,18 @@
import binascii
import glob
import logging
import multiprocessing
import os
import os.path
import plistlib
import shutil
import sqlite3
import tempfile
from concurrent.futures import (
ALL_COMPLETED,
FIRST_COMPLETED,
Future,
ThreadPoolExecutor,
wait,
)
from pathlib import Path
from typing import Optional
from iphone_backup_decrypt import EncryptedBackup
from iphone_backup_decrypt import google_iphone_dataprotection
from iphone_backup_decrypt.utils import FilePlist
from .decrypt_config import DEFAULT_DECRYPT_WORKERS, MAX_DECRYPT_WORKERS
from iOSbackup import iOSbackup
log = logging.getLogger(__name__)
# Import pbkdf2_hmac from the same source iphone_backup_decrypt uses internally,
# so our key derivation is consistent with theirs.
try:
from fastpbkdf2 import pbkdf2_hmac
except ImportError:
import Crypto.Hash.SHA1
import Crypto.Hash.SHA256
import Crypto.Protocol.KDF
_HASH_FNS = {"sha1": Crypto.Hash.SHA1, "sha256": Crypto.Hash.SHA256}
def pbkdf2_hmac(hash_name, password, salt, iterations, dklen=None):
return Crypto.Protocol.KDF.PBKDF2(
password, salt, dklen, iterations, hmac_hash_module=_HASH_FNS[hash_name]
)
class MVTEncryptedBackup(EncryptedBackup):
"""Extends EncryptedBackup with derived key export/import.
NOTE: This subclass relies on internal APIs of iphone_backup_decrypt
(specifically _read_and_unlock_keybag, _keybag, and the Keybag class
internals). Pinned to iphone_backup_decrypt==0.10.0.
"""
def __init__(self, *, backup_directory, passphrase=None, derived_key=None):
if passphrase:
super().__init__(backup_directory=backup_directory, passphrase=passphrase)
self._derived_key = None # Will be set after keybag unlock
elif derived_key:
self._init_without_passphrase(backup_directory, derived_key)
else:
raise ValueError("Either passphrase or derived_key must be provided")
def _init_without_passphrase(self, backup_directory, derived_key):
"""Replicate parent __init__ state without requiring a passphrase."""
self.decrypted = False
self._backup_directory = os.path.expandvars(backup_directory)
self._passphrase = None
self._manifest_plist_path = os.path.join(
self._backup_directory, "Manifest.plist"
)
self._manifest_plist = None
self._manifest_db_path = os.path.join(self._backup_directory, "Manifest.db")
self._keybag = None
self._unlocked = False
self._temporary_folder = tempfile.mkdtemp()
self._temp_decrypted_manifest_db_path = os.path.join(
self._temporary_folder, "Manifest.db"
)
self._temp_manifest_db_conn = None
self._derived_key = derived_key # 32 raw bytes
def _read_and_unlock_keybag(self):
"""Override to capture derived key on password unlock, or use
a pre-derived key to skip PBKDF2."""
if self._unlocked:
return self._unlocked
with open(self._manifest_plist_path, "rb") as infile:
self._manifest_plist = plistlib.load(infile)
self._keybag = google_iphone_dataprotection.Keybag(
self._manifest_plist["BackupKeyBag"]
)
if self._derived_key:
# Skip PBKDF2, unwrap class keys directly with pre-derived key
self._unlocked = _unlock_keybag_with_derived_key(
self._keybag, self._derived_key
)
else:
# Normal path: full PBKDF2 derivation, capturing the intermediate key
self._unlocked, self._derived_key = _unlock_keybag_and_capture_key(
self._keybag, self._passphrase
)
self._passphrase = None
if not self._unlocked:
raise ValueError("Failed to decrypt keys: incorrect passphrase?")
return True
def get_decryption_key(self):
"""Return derived key as hex string (64 chars / 32 bytes)."""
if self._derived_key is None:
raise ValueError("No derived key available")
return self._derived_key.hex()
def extract_file_by_id(self, *, file_id, file_bplist, output_filename):
"""Extract one manifest entry without loading the whole file into memory."""
self._read_and_unlock_keybag()
file_plist = FilePlist(file_bplist)
if file_plist.encryption_key is None:
source_filename = os.path.join(
self._backup_directory, file_id[:2], file_id
)
shutil.copy2(source_filename, output_filename)
return
inner_key = self._keybag.unwrapKeyForClass(
file_plist.protection_class, file_plist.encryption_key
)
self._decrypt_file_to_disk(
file_id=file_id,
key=inner_key,
file_plist=file_plist,
output_filepath=output_filename,
)
def _unlock_keybag_with_derived_key(keybag, passphrase_key):
"""Unlock keybag class keys using a pre-derived passphrase_key,
skipping the expensive PBKDF2 rounds."""
WRAP_PASSPHRASE = 2
for classkey in keybag.classKeys.values():
if b"WPKY" not in classkey:
continue
if classkey[b"WRAP"] & WRAP_PASSPHRASE:
k = google_iphone_dataprotection._AESUnwrap(
passphrase_key, classkey[b"WPKY"]
)
if not k:
return False
classkey[b"KEY"] = k
return True
def _unlock_keybag_and_capture_key(keybag, passphrase):
"""Run full PBKDF2 key derivation and AES unwrap, returning
(success, passphrase_key) so the derived key can be exported."""
passphrase_round1 = pbkdf2_hmac(
"sha256", passphrase, keybag.attrs[b"DPSL"], keybag.attrs[b"DPIC"], 32
)
passphrase_key = pbkdf2_hmac(
"sha1", passphrase_round1, keybag.attrs[b"SALT"], keybag.attrs[b"ITER"], 32
)
WRAP_PASSPHRASE = 2
for classkey in keybag.classKeys.values():
if b"WPKY" not in classkey:
continue
if classkey[b"WRAP"] & WRAP_PASSPHRASE:
k = google_iphone_dataprotection._AESUnwrap(
passphrase_key, classkey[b"WPKY"]
)
if not k:
return False, None
classkey[b"KEY"] = k
return True, passphrase_key
class DecryptBackup:
"""This class provides functions to decrypt an encrypted iTunes backup
@@ -187,68 +26,19 @@ class DecryptBackup:
"""
def __init__(
self,
backup_path: str,
dest_path: Optional[str] = None,
max_workers: int = DEFAULT_DECRYPT_WORKERS,
) -> None:
def __init__(self, backup_path: str, dest_path: Optional[str] = None) -> None:
"""Decrypts an encrypted iOS backup.
:param backup_path: Path to the encrypted backup folder
:param dest_path: Path to the folder where to store the decrypted backup
"""
self.backup_path = os.path.abspath(backup_path)
self.dest_path = dest_path
if not 1 <= max_workers <= MAX_DECRYPT_WORKERS:
raise ValueError(f"max_workers must be between 1 and {MAX_DECRYPT_WORKERS}")
self.max_workers = max_workers
self._backup: Optional[MVTEncryptedBackup] = None
self._decryption_key: Optional[str] = None
self._backup = None
self._decryption_key = None
def can_process(self) -> bool:
return self._backup is not None
def _process_file(
self,
*,
file_id: str,
file_bplist: bytes,
output_path: Path,
relative_path: str,
domain: str,
) -> None:
assert self._backup is not None
self._backup.extract_file_by_id(
file_id=file_id,
file_bplist=file_bplist,
output_filename=str(output_path),
)
log.info(
"Decrypted file %s [%s] to %s/%s",
relative_path,
domain,
output_path.parent,
file_id,
)
@staticmethod
def _wait_for_files(
pending: dict[Future[None], str], *, all_files: bool = False
) -> None:
if not pending:
return
done, _ = wait(
pending,
return_when=ALL_COMPLETED if all_files else FIRST_COMPLETED,
)
for future in done:
relative_path = pending.pop(future)
try:
future.result()
except Exception as exc:
log.error("Failed to decrypt file %s: %s", relative_path, exc)
@staticmethod
def is_encrypted(backup_path: str) -> bool:
"""Query Manifest.db file to see if it's encrypted or not.
@@ -268,6 +58,21 @@ class DecryptBackup:
finally:
conn.close()
def _process_file(
self, relative_path: str, domain: str, item, file_id: str, item_folder: str
) -> None:
assert self._backup is not None
self._backup.getFileDecryptedCopy(
manifestEntry=item, targetName=file_id, targetFolder=item_folder
)
log.info(
"Decrypted file %s [%s] to %s/%s",
relative_path,
domain,
item_folder,
file_id,
)
def process_backup(self) -> None:
assert self._backup is not None
assert self.dest_path is not None
@@ -276,71 +81,53 @@ class DecryptBackup:
os.makedirs(self.dest_path)
manifest_path = os.path.join(self.dest_path, "Manifest.db")
# Extract a decrypted Manifest.db to the destination folder.
self._backup.save_manifest_file(output_filename=manifest_path)
# We extract a decrypted Manifest.db.
self._backup.getManifestDB()
# We store it to the destination folder.
shutil.copy(self._backup.manifestDB, manifest_path)
# Iterate over all files in the backup and decrypt them,
# preserving the XX/file_id directory structure that downstream
# modules expect.
backup_root = Path(self.backup_path).resolve()
dest_root = Path(self.dest_path).resolve()
pending: dict[Future[None], str] = {}
with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
with self._backup.manifest_db_cursor() as cur:
cur.execute(
"SELECT fileID, domain, relativePath, file FROM Files WHERE flags=1"
)
for file_id, domain, relative_path, file_bplist in cur:
# This may be a partial backup. Skip files from the manifest
# which do not exist locally.
source_file_path = backup_root / file_id[:2] / file_id
if not source_file_path.resolve().is_relative_to(backup_root):
log.warning("Skipping unsafe file_id: %r", file_id)
continue
if not os.path.exists(source_file_path):
log.debug(
"Skipping file %s. File not found in encrypted "
"backup directory.",
source_file_path,
)
continue
pool = multiprocessing.Pool(multiprocessing.cpu_count())
output_path = dest_root / file_id[:2] / file_id
if not output_path.resolve().is_relative_to(dest_root):
log.warning("Skipping unsafe file_id: %r", file_id)
continue
output_path.parent.mkdir(parents=True, exist_ok=True)
for item in self._backup.getBackupFilesList():
try:
file_id = item["backupFile"]
relative_path = item["relativePath"]
domain = item["domain"]
if self.max_workers == 1:
try:
self._process_file(
file_id=file_id,
file_bplist=file_bplist,
output_path=output_path,
relative_path=relative_path,
domain=domain,
)
except Exception as exc:
log.error(
"Failed to decrypt file %s: %s",
relative_path,
exc,
)
continue
future = executor.submit(
self._process_file,
file_id=file_id,
file_bplist=file_bplist,
output_path=output_path,
relative_path=relative_path,
domain=domain,
# This may be a partial backup. Skip files from the manifest
# which do not exist locally.
source_file_path = os.path.join(self.backup_path, file_id[0:2], file_id)
if not Path(source_file_path).resolve().is_relative_to(Path(self.backup_path).resolve()):
log.warning("Skipping unsafe file_id: %r", file_id)
continue
if not os.path.exists(source_file_path):
log.debug(
"Skipping file %s. File not found in encrypted backup directory.",
source_file_path,
)
pending[future] = relative_path
if len(pending) >= self.max_workers:
self._wait_for_files(pending)
continue
self._wait_for_files(pending, all_files=True)
item_folder = os.path.join(self.dest_path, file_id[0:2]) # type: ignore[arg-type]
if not Path(os.path.join(item_folder, file_id)).resolve().is_relative_to(Path(self.dest_path).resolve()):
log.warning("Skipping unsafe file_id: %r", file_id)
continue
if not os.path.exists(item_folder):
os.makedirs(item_folder)
# iOSBackup getFileDecryptedCopy() claims to read a "file"
# parameter but the code actually is reading the "manifest" key.
# Add manifest plist to both keys to handle this.
item["manifest"] = item["file"]
pool.apply_async(
self._process_file,
args=(relative_path, domain, item, file_id, item_folder),
)
except Exception as exc:
log.error("Failed to decrypt file %s: %s", relative_path, exc)
pool.close()
pool.join()
# Copying over the root plist files as well.
for file_name in os.listdir(self.backup_path):
@@ -381,23 +168,20 @@ class DecryptBackup:
return
try:
self._backup = MVTEncryptedBackup(
backup_directory=self.backup_path,
passphrase=password,
self._backup = iOSbackup(
udid=os.path.basename(self.backup_path),
cleartextpassword=password,
backuproot=os.path.dirname(self.backup_path),
)
# Eagerly trigger keybag unlock so wrong-password errors
# surface here rather than later during process_backup().
self._backup.test_decryption()
except Exception as exc:
self._backup = None
if (
isinstance(exc, ValueError)
and "passphrase" in str(exc).lower()
isinstance(exc, KeyError)
and len(exc.args) > 0
and exc.args[0] == b"KEY"
):
log.critical("Failed to decrypt backup. Password is probably wrong.")
elif (
isinstance(exc, FileNotFoundError)
and hasattr(exc, "filename")
and os.path.basename(exc.filename) == "Manifest.plist"
):
log.critical(
@@ -440,14 +224,12 @@ class DecryptBackup:
try:
key_bytes_raw = binascii.unhexlify(key_bytes)
self._backup = MVTEncryptedBackup(
backup_directory=self.backup_path,
derived_key=key_bytes_raw,
self._backup = iOSbackup(
udid=os.path.basename(self.backup_path),
derivedkey=key_bytes_raw,
backuproot=os.path.dirname(self.backup_path),
)
# Eagerly trigger keybag unlock so wrong-key errors surface here.
self._backup.test_decryption()
except Exception as exc:
self._backup = None
log.exception(exc)
log.critical(
"Failed to decrypt backup. Did you provide the correct key file?"
@@ -458,7 +240,7 @@ class DecryptBackup:
if not self._backup:
return
self._decryption_key = self._backup.get_decryption_key()
self._decryption_key = self._backup.getDecryptionKey()
log.info(
'Derived decryption key for backup at path %s is: "%s"',
self.backup_path,
-9
View File
@@ -1,9 +0,0 @@
# Mobile Verification Toolkit (MVT)
# Copyright (c) 2026 The MVT Authors.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
"""Configuration shared by the iOS CLI and backup decryption implementation."""
DEFAULT_DECRYPT_WORKERS = 4
MAX_DECRYPT_WORKERS = 32
+1 -8
View File
@@ -3,16 +3,9 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .backup_info import BackupInfo
from .configuration_profiles import ConfigurationProfiles
from .manifest import Manifest
from .profile_events import ProfileEvents
BACKUP_MODULES: list[type[MVTModule]] = [
BackupInfo,
ConfigurationProfiles,
Manifest,
ProfileEvents,
]
BACKUP_MODULES = [BackupInfo, ConfigurationProfiles, Manifest, ProfileEvents]
+1 -3
View File
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .analytics import Analytics
from .analytics_ios_versions import AnalyticsIOSVersions
from .cache_files import CacheFiles
@@ -17,7 +15,7 @@ from .webkit_indexeddb import WebkitIndexedDB
from .webkit_localstorage import WebkitLocalStorage
from .webkit_safariviewservice import WebkitSafariViewService
FS_MODULES: list[type[MVTModule]] = [
FS_MODULES = [
CacheFiles,
Filesystem,
Netusage,
+2 -6
View File
@@ -82,9 +82,7 @@ class Filesystem(IOSExtraction):
try:
dir_path = os.path.join(root, dir_name)
result = {
"path": os.path.relpath(dir_path, self.target_path).replace(
os.sep, "/"
),
"path": os.path.relpath(dir_path, self.target_path),
"modified": convert_unix_to_iso(os.stat(dir_path).st_mtime),
}
except Exception:
@@ -96,9 +94,7 @@ class Filesystem(IOSExtraction):
try:
file_path = os.path.join(root, file_name)
result = {
"path": os.path.relpath(file_path, self.target_path).replace(
os.sep, "/"
),
"path": os.path.relpath(file_path, self.target_path),
"modified": convert_unix_to_iso(os.stat(file_path).st_mtime),
}
except Exception:
+1 -5
View File
@@ -3,8 +3,6 @@
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
from mvt.common.module import MVTModule
from .applications import Applications
from .calendar import Calendar
from .calls import Calls
@@ -28,9 +26,8 @@ from .tcc import TCC
from .webkit_resource_load_statistics import WebkitResourceLoadStatistics
from .webkit_session_resource_log import WebkitSessionResourceLog
from .whatsapp import Whatsapp
from .whatsapp_contacts import WhatsappContacts
MIXED_MODULES: list[type[MVTModule]] = [
MIXED_MODULES = [
Calls,
ChromeFavicon,
ChromeHistory,
@@ -50,7 +47,6 @@ MIXED_MODULES: list[type[MVTModule]] = [
WebkitResourceLoadStatistics,
WebkitSessionResourceLog,
Whatsapp,
WhatsappContacts,
Shortcuts,
Applications,
Calendar,
Loaded 100 of 175 files, more files were not shown because too many files have changed in this diff. Show more