Merge branch 'main' into fix/native-docker-runners

Strip only a whole www. prefix from parsed domains

.github/workflows/publish-release-docker.yml

@@ -14,10 +14,10 @@ env:
   REGISTRY: ghcr.io
   IMAGE_NAME: ${{ github.repository }}
 
-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+# Build each architecture natively, then publish the combined image manifests.
 jobs:
   build-and-push-image:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.architecture.runner }}
     # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
     permissions:
       contents: read
@@ -26,7 +26,15 @@ jobs:
       id-token: write
       #
     strategy:
+      fail-fast: false
       matrix:
+        architecture:
+          - platform: linux/amd64
+            runner: ubuntu-24.04
+            name: amd64
+          - platform: linux/arm64
+            runner: ubuntu-24.04-arm
+            name: arm64
         platform:
           - dockerfile: "Dockerfile"
             tag-suffix: ""
@@ -61,24 +69,95 @@ jobs:
             type=raw,enable=${{ 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
       # 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.
+      # Push by digest so architecture builds do not overwrite shared image tags.
       - name: Build and push Docker image
         id: push
         uses: docker/build-push-action@v7
         with:
           file: ${{ matrix.platform.dockerfile }}
           context: .
-          platforms: linux/amd64,linux/arm64
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
+          platforms: ${{ matrix.architecture.platform }}
+          outputs: type=image,name=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
           labels: ${{ steps.meta.outputs.labels }}
           provenance: mode=max
           sbom: true
+      - name: Export image digest
+        env:
+          DIGEST: ${{ steps.push.outputs.digest }}
+        run: |
+          mkdir -p "${RUNNER_TEMP}/digests"
+          touch "${RUNNER_TEMP}/digests/${DIGEST#sha256:}"
+      - name: Upload image digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ matrix.platform.dockerfile }}-${{ matrix.architecture.name }}
+          path: ${{ runner.temp }}/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  publish-manifests:
+    needs: build-and-push-image
+    runs-on: ubuntu-24.04
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        platform:
+          - dockerfile: "Dockerfile"
+            tag-suffix: ""
+          - dockerfile: "Dockerfile.ios"
+            tag-suffix: "-ios"
+          - dockerfile: "Dockerfile.android"
+            tag-suffix: "-android"
+    steps:
+      - name: Download image digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-${{ matrix.platform.dockerfile }}-*
+          path: ${{ runner.temp }}/digests
+          merge-multiple: true
+      - name: Log in to the Container registry
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v6
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          flavor: |
+            latest=false
+          tags: |
+            type=raw,value=latest,enable={{ is_default_branch }},suffix=${{ matrix.platform.tag-suffix }}
+            type=raw,enable=${{ github.event_name == 'release' || github.ref_type == 'tag' }},value=stable,suffix=${{ matrix.platform.tag-suffix }}
+            type=raw,enable=${{ github.event_name == 'release' }},value=${{ github.event.release.tag_name }},suffix=${{ matrix.platform.tag-suffix }}
+            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 }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v4
+      - name: Publish multi-platform image
+        working-directory: ${{ runner.temp }}/digests
+        env:
+          METADATA_JSON: ${{ steps.meta.outputs.json }}
+        run: |
+          mapfile -t tags < <(jq -r '.tags[]' <<< "$METADATA_JSON")
+          tag_args=()
+          for tag in "${tags[@]}"; do
+            tag_args+=(--tag "$tag")
+          done
+          images=()
+          for digest in *; do
+            images+=("${REGISTRY}/${IMAGE_NAME}@sha256:${digest}")
+          done
+          test "${#images[@]}" -eq 2
+          docker buildx imagetools create "${tag_args[@]}" "${images[@]}"
+          docker buildx imagetools inspect "${tags[0]}"

src/mvt/android/artifacts/dumpsys_accessibility.py

@@ -10,8 +10,45 @@ 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:
@@ -20,11 +57,22 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
                     )
                     continue
 
-            self.alertstore.medium(
-                f'Found accessibility service: "{result["component"]}"',
-                "",
-                result,
+            # 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)
 
     def parse(self, content: str) -> None:
         """
@@ -36,6 +84,13 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
 
         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
 
@@ -44,6 +99,10 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
             if user_match:
                 user_id = int(user_match.group(1))
 
+            count_match = re.search(r"installedServiceCount=(\d+)", line)
+            if count_match:
+                installed_counts[user_id] = int(count_match.group(1))
+
             stripped = line.strip()
             state_match = re.match(
                 r"(?i)(installed|enabled|binding|bound|crashed) services\s*:\s*\{(.*)",
@@ -51,6 +110,7 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
             )
             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
@@ -79,24 +139,65 @@ class DumpsysAccessibilityArtifact(AndroidArtifact):
                 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:
-        package_name, service_name = component.split("/", 1)
-        return {
-            "user_id": user_id,
-            "component": component,
-            "package_name": package_name,
-            "service_name": service_name,
-            "installed": False,
-            "enabled": False,
-            "binding": False,
-            "bound": False,
-            "crashed": False,
-            "accessibility_tool": False,
-        }
+        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

src/mvt/android/cmd_check_bugreport.py

@@ -3,14 +3,19 @@
 # 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 ZipFile
+from zipfile import BadZipFile, ZipFile
 
 from mvt.android.artifacts.getprop import GetProp
-from mvt.android.modules.bugreport.base import BugReportModule
+from mvt.android.modules.bugreport.base import (
+    DUMPSTATE_ENTRY_POINTS,
+    BugReportModule,
+)
 from mvt.common.command import Command
 from mvt.common.indicators import Indicators
 from mvt.common.module import MVTModule
@@ -88,6 +93,48 @@ 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)

src/mvt/android/modules/bugreport/base.py

@@ -6,6 +6,7 @@ import datetime
 import fnmatch
 import logging
 import os
+import re
 from pathlib import Path
 from typing import List, Optional
 from zipfile import ZipFile
@@ -13,6 +14,15 @@ 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."""
@@ -87,7 +97,9 @@ class BugReportModule(MVTModule):
         return data
 
     def _get_dumpstate_file(self) -> Optional[bytes]:
-        main = self._get_files_by_pattern("main_entry.txt")
+        main_entry, dumpstate_log, dumpsys_txt = DUMPSTATE_ENTRY_POINTS
+
+        main = self._get_files_by_pattern(main_entry)
         if main:
             main_content = self._get_file_content(main[0])
             try:
@@ -95,11 +107,11 @@ 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])
 
@@ -122,6 +134,12 @@ class BugReportModule(MVTModule):
                     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)

src/mvt/android/modules/bugreport/dumpsys_accessibility.py

@@ -48,9 +48,22 @@ class DumpsysAccessibility(DumpsysAccessibilityArtifact, BugReportModule):
         )
         self.parse(content)
 
+        listed = unnamed = 0
         for result in self.results:
-            self.log.info('Found accessibility service "%s"', result.get("component"))
+            if result.get("component"):
+                listed += 1
+                self.log.info(
+                    'Found accessibility service "%s"', result.get("component")
+                )
+                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(
-            "Identified a total of %d accessibility services", len(self.results)
+            "Identified a total of %d accessibility services (%d more stated by "
+            "the dump without a component name)",
+            listed,
+            unnamed,
         )

src/mvt/common/url.py

@@ -349,7 +349,9 @@ class URL:
             return tld_obj
         if tld_obj is None:
             return ""
-        return tld_obj.parsed_url.netloc.lower().lstrip("www.")
+        # 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.")
 
     def get_top_level(self) -> str:
         """Get only the top-level domain from a URL.

tests/android/test_artifact_dumpsys_accessibility.py

@@ -35,11 +35,16 @@ class TestDumpsysAccessibilityArtifact:
 
         assert len(da.results) == 0
         da.parse(data)
-        assert len(da.results) == 1
+        # One named service, plus one count-only record: the dump states
+        # `installedServiceCount=2` and names only one component.
+        assert len(da.results) == 2
         assert da.results[0]["package_name"] == "com.malware.accessibility"
         assert da.results[0]["service_name"] == "com.malware.service.malwareservice"
         assert da.results[0]["enabled"] is True
-        assert da.results[0]["installed"] is False
+        # This fixture never prints an `installed services:` section, so the
+        # dump does not state the installed status. Reporting False would turn
+        # "not stated" into "not installed", so it reads None here.
+        assert da.results[0]["installed"] is None
 
     def test_accessibility_service_alert(self):
         da = DumpsysAccessibilityArtifact()
@@ -50,9 +55,11 @@ class TestDumpsysAccessibilityArtifact:
 
         da.check_indicators()
 
-        assert len(da.alertstore.alerts) == 1
+        assert len(da.alertstore.alerts) == 2
         assert da.alertstore.alerts[0].level == AlertLevel.MEDIUM
         assert da.alertstore.alerts[0].event == da.results[0]
+        assert da.alertstore.alerts[1].level == AlertLevel.LOW
+        assert da.alertstore.alerts[1].event == da.results[1]
 
     def test_same_component_is_kept_for_each_user(self):
         da = DumpsysAccessibilityArtifact()
@@ -84,7 +91,11 @@ User state[attributes:{id=10
         assert len(da.alertstore.alerts) == 0
         da.check_indicators()
         assert len(da.alertstore.alerts) == len(da.results)
-        assert da.alertstore.count(AlertLevel.MEDIUM) == 3
+        # Every service in this fixture is installed and switched off
+        # (`enabled services:{}` is printed and empty), so the three non-IOC
+        # findings are LOW, not MEDIUM. The IOC match is unaffected by the
+        # state.
+        assert da.alertstore.count(AlertLevel.LOW) == 3
         assert da.alertstore.count(AlertLevel.CRITICAL) == 1
         critical_alert = next(
             alert

tests/android/test_artifact_dumpsys_accessibility_count.py

@@ -0,0 +1,149 @@
+# 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/
+"""The dump's own installed-service count must survive into the artifact.
+
+Most builds never print the `installed services: {…}` block; they state `installedServiceCount=N` in the user's `attributes:{…}` line and
+list nothing. Dropping that number makes an artifact that says "no
+accessibility services" about a dump that said there are five.
+"""
+
+from mvt.android.artifacts.dumpsys_accessibility import DumpsysAccessibilityArtifact
+from mvt.common.alerts import AlertLevel
+
+from ..utils import get_artifact
+
+AOSP_NO_LIST = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[
+     attributes:{id=0, touchExplorationEnabled=false, installedServiceCount=5}
+     Bound services:{}
+     Enabled services:{}
+     Binding services:{}
+     Crashed services:{}
+"""
+
+ONE_UI_WITH_LIST = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, installedServiceCount=2}
+  installed services: {
+    0 : com.example.app/com.example.app.Service
+    1 : com.other.app/.Helper
+  }
+  enabled services: {
+  }
+"""
+
+TWO_USERS = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, installedServiceCount=1}
+  installed services: {
+    0 : com.example.app/com.example.app.Service
+  }
+User state[attributes:{id=95, installedServiceCount=3}
+     Enabled services:{}
+"""
+
+PARTIAL_TWO_USERS = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, installedServiceCount=3}
+     Enabled services:{{com.example.app/com.example.app.Service}}
+User state[attributes:{id=10, installedServiceCount=1}
+     Enabled services:{{com.other.app/.Helper}}
+"""
+
+ZERO_COUNT = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, installedServiceCount=0}
+     Enabled services:{}
+"""
+
+
+def _parse(content):
+    artifact = DumpsysAccessibilityArtifact()
+    artifact.results = []
+    artifact.parse(content)
+    return artifact
+
+
+class TestAccessibilityInstalledServiceCount:
+    def test_stated_count_without_a_list_is_kept(self):
+        artifact = _parse(AOSP_NO_LIST)
+        assert len(artifact.results) == 1
+        record = artifact.results[0]
+        assert record["installed_service_count"] == 5
+        assert record["component"] is None
+        # Every state flag stays unknown: the dump named no service to which a
+        # state could belong.
+        assert record["installed"] is None
+        assert record["enabled"] is None
+
+    def test_a_stated_count_is_reported_as_low(self):
+        artifact = _parse(AOSP_NO_LIST)
+        artifact.check_indicators()
+        alerts = artifact.alertstore.alerts
+        assert len(alerts) == 1
+        # A count is a coverage statement, not a running service: it must not
+        # compete with a service the dump says is enabled.
+        assert alerts[0].level == AlertLevel.LOW
+        assert "does not list their component names" in alerts[0].message
+        assert "5 installed" in alerts[0].message
+
+    def test_a_listed_user_carries_the_count_on_each_service(self):
+        artifact = _parse(ONE_UI_WITH_LIST)
+        assert len(artifact.results) == 2
+        assert {record["installed_service_count"] for record in artifact.results} == {2}
+        assert all(record["component"] for record in artifact.results)
+
+    def test_only_the_unlisted_user_gets_a_count_record(self):
+        artifact = _parse(TWO_USERS)
+        listed = [record for record in artifact.results if record["component"]]
+        unlisted = [record for record in artifact.results if not record["component"]]
+        assert [record["user_id"] for record in listed] == [0]
+        assert [record["user_id"] for record in unlisted] == [95]
+        assert unlisted[0]["installed_service_count"] == 3
+
+    def test_a_zero_count_adds_nothing(self):
+        # "Zero installed" is a negative result the empty section already
+        # states; a record for it would be noise.
+        assert _parse(ZERO_COUNT).results == []
+
+    def test_a_partly_named_count_reports_the_unnamed_rest(self):
+        # The Android 14 fixture states `installedServiceCount=2` and names one
+        # enabled component. The listing is incomplete, and must not read as
+        # complete.
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        with open(
+            get_artifact("android_data/dumpsys_accessibility_v14_or_later.txt")
+        ) as handle:
+            artifact.parse(handle.read())
+        unlisted = [record for record in artifact.results if not record["component"]]
+        assert len(unlisted) == 1
+        assert unlisted[0]["installed_service_count"] == 2
+        assert unlisted[0]["unnamed_service_count"] == 1
+
+        artifact.check_indicators()
+        low = [
+            alert
+            for alert in artifact.alertstore.alerts
+            if alert.level == AlertLevel.LOW
+        ]
+        assert len(low) == 1
+        assert "only 1 of them (1 unnamed)" in low[0].message
+
+    def test_the_unnamed_rest_is_counted_per_user(self):
+        # User 0 names one of three, user 10 names its only one: the gap
+        # belongs to user 0 alone.
+        artifact = _parse(PARTIAL_TWO_USERS)
+        unlisted = [record for record in artifact.results if not record["component"]]
+        assert [
+            (record["user_id"], record["unnamed_service_count"]) for record in unlisted
+        ] == [(0, 2)]
+
+    def test_a_fully_named_count_adds_nothing(self):
+        artifact = _parse(ONE_UI_WITH_LIST)
+        assert all(
+            record["unnamed_service_count"] is None for record in artifact.results
+        )

tests/android/test_artifact_dumpsys_accessibility_state.py

@@ -0,0 +1,155 @@
+# 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/
+"""Installed is not the same as enabled, and the dump says which.
+
+Two things this guards:
+
+  * a section the dump never printed must read as None ("not stated"), not as
+    False ("not enabled");
+  * the alert must name the state, instead of firing identically on a device
+    where nothing is switched on and one where something is bound.
+"""
+
+from types import SimpleNamespace
+
+from mvt.android.artifacts.dumpsys_accessibility import DumpsysAccessibilityArtifact
+from mvt.common.alerts import AlertLevel
+
+from ..utils import get_artifact
+
+NO_STATE_SECTIONS = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, currentUser=true}
+  installed services: {
+    0 : com.example.app/com.example.app.Service
+  }
+"""
+
+ENABLED_BLOCK = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, currentUser=true}
+  installed services: {
+    0 : com.example.app/com.example.app.Service
+    1 : com.other.app/.Helper
+  }
+  enabled services: {
+    0 : com.other.app/.Helper
+  }
+  bound services:{
+    0 : com.other.app/.Helper
+  }
+"""
+
+# User 0 prints only `installed services`, user 10 only `Enabled services`.
+# Neither section speaks for the other user.
+TWO_USERS_DIFFERENT_SECTIONS = """\
+ACCESSIBILITY MANAGER (dumpsys accessibility)
+User state[attributes:{id=0, currentUser=true}
+  installed services: {
+    0 : com.example.app/com.example.app.Service
+  }
+User state[attributes:{id=10, currentUser=false}
+     Enabled services:{{com.other.app/.Helper}}
+"""
+
+
+class _IndicatorsMatching:
+    """Minimal stand-in: matches one package id, like the STIX2 loader would."""
+
+    def __init__(self, package_name: str) -> None:
+        self.package_name = package_name
+
+    def check_app_id(self, app_id):
+        if app_id != self.package_name:
+            return None
+        return SimpleNamespace(
+            message=f"Found a known suspicious app: {app_id}", ioc={"value": app_id}
+        )
+
+
+class TestAccessibilityServiceState:
+    def _parse(self, content):
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        artifact.parse(content)
+        return {r["component"]: r for r in artifact.results}
+
+    def test_absent_sections_leave_the_state_unknown(self):
+        # None, not False: a build that does not print the sections says
+        # nothing about what is enabled, and that must not read as "nothing".
+        state = self._parse(NO_STATE_SECTIONS)[
+            "com.example.app/com.example.app.Service"
+        ]
+        assert state["installed"] is True
+        assert state["enabled"] is None
+        assert state["bound"] is None
+
+    def test_enabled_and_bound_are_attributed_per_service(self):
+        results = self._parse(ENABLED_BLOCK)
+        installed_only = results["com.example.app/com.example.app.Service"]
+        active = results["com.other.app/.Helper"]
+        assert (installed_only["enabled"], installed_only["bound"]) == (False, False)
+        assert (active["enabled"], active["bound"]) == (True, True)
+
+    def test_alert_message_carries_the_state(self):
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        with open(get_artifact("android_data/dumpsys_accessibility.txt")) as handle:
+            artifact.parse(handle.read())
+        artifact.check_indicators()
+        assert artifact.alertstore.alerts
+        assert all("installed" in alert.message for alert in artifact.alertstore.alerts)
+
+    def test_a_switched_off_service_is_low_and_a_running_one_medium(self):
+        # A service the dump says is OFF still reaches the analyst, but must not
+        # compete with one that is actually bound. "Not stated" is not "off".
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        artifact.parse(ENABLED_BLOCK)
+        artifact.check_indicators()
+        by_level = {}
+        for alert in artifact.alertstore.alerts:
+            by_level.setdefault(alert.level, []).append(alert.message)
+        assert artifact.alertstore.count(AlertLevel.LOW) == 1
+        assert artifact.alertstore.count(AlertLevel.MEDIUM) == 1
+        assert "com.example.app" in by_level[AlertLevel.LOW][0]
+        assert "com.other.app" in by_level[AlertLevel.MEDIUM][0]
+
+    def test_an_unstated_enabled_state_stays_medium(self):
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        artifact.parse(NO_STATE_SECTIONS)
+        artifact.check_indicators()
+        assert artifact.alertstore.count(AlertLevel.MEDIUM) == 1
+        assert artifact.alertstore.count(AlertLevel.LOW) == 0
+
+    def test_a_disabled_service_is_still_matched_against_indicators(self):
+        # The state decides the severity of an ordinary finding, never whether
+        # the package is compared with the IOC feeds.
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        artifact.parse(ENABLED_BLOCK)
+        artifact.indicators = _IndicatorsMatching("com.example.app")
+        artifact.check_indicators()
+        assert artifact.alertstore.count(AlertLevel.CRITICAL) == 1
+        assert artifact.alertstore.count(AlertLevel.LOW) == 0
+
+    def test_printed_sections_are_tracked_per_user(self):
+        artifact = DumpsysAccessibilityArtifact()
+        artifact.results = []
+        artifact.parse(TWO_USERS_DIFFERENT_SECTIONS)
+        by_user = {r["user_id"]: r for r in artifact.results}
+        # User 0's enabled state is not stated, so it is unknown, not off.
+        assert (by_user[0]["installed"], by_user[0]["enabled"]) == (True, None)
+        # User 10's installed state is not stated either.
+        assert (by_user[10]["installed"], by_user[10]["enabled"]) == (None, True)
+
+        artifact.check_indicators()
+        assert artifact.alertstore.count(AlertLevel.LOW) == 0
+        assert artifact.alertstore.count(AlertLevel.MEDIUM) == 2
+        assert not any(
+            "installed, not enabled" in alert.message
+            for alert in artifact.alertstore.alerts
+        )

tests/android/test_bugreport_section_extraction.py

@@ -0,0 +1,42 @@
+# 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/
+"""A section ends at the next section, not at a timing line printed inside it."""
+
+from mvt.android.modules.bugreport.base import BugReportModule
+
+# dumpstate prints a section's duration when that section finishes, which can
+# land in the middle of the section currently being written.
+DUMPSTATE = """\
+------ SYSTEM PROPERTIES (getprop) ------
+[nfc.initialized]: [true]
+------ 0.101s was the duration of 'DROPBOX SYSTEM SERVER CRASHES' ------
+[ro.build.version.sdk]: [30]
+[ro.product.model]: [SM-A305F]
+------ 0.064s was the duration of 'SYSTEM PROPERTIES' ------
+------ STORAGE INFO (df) ------
+/dev/root  2.9G
+"""
+
+
+class TestExtractCommandSection:
+    def test_a_foreign_timing_line_does_not_end_the_section(self):
+        section = BugReportModule.extract_command_section(
+            DUMPSTATE, "------ SYSTEM PROPERTIES"
+        )
+        assert "[ro.product.model]: [SM-A305F]" in section
+        assert section.count("\n") == 2
+
+    def test_the_next_section_is_still_the_boundary(self):
+        section = BugReportModule.extract_command_section(
+            DUMPSTATE, "------ SYSTEM PROPERTIES"
+        )
+        assert "STORAGE INFO" not in section
+        assert "/dev/root" not in section
+
+    def test_timing_lines_are_not_returned_as_content(self):
+        section = BugReportModule.extract_command_section(
+            DUMPSTATE, "------ SYSTEM PROPERTIES"
+        )
+        assert "was the duration of" not in section

tests/android/test_check_bugreport_wrapper.py

@@ -0,0 +1,56 @@
+# Mobile Verification Toolkit (MVT)
+# 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/
+"""An OEM wrapper archive must not read as an empty bug report.
+
+MIUI / HyperOS hands out a zip of app logs with the real
+`bugreport-<device>-<timestamp>.zip` nested inside. The outer archive has
+none of the entry points the modules read, so every module
+reported it found nothing and the command still exited 0 — an empty analysis
+that looks like a finished one.
+"""
+
+import io
+import zipfile
+
+from mvt.android.cmd_check_bugreport import CmdAndroidCheckBugreport
+
+DUMPSTATE = "== dumpstate: 2026-01-01 00:00:00\nDUMP OF SERVICE package:\n"
+
+
+def _inner_zip() -> bytes:
+    buffer = io.BytesIO()
+    with zipfile.ZipFile(buffer, "w") as inner:
+        inner.writestr("main_entry.txt", "bugreport-test-2026-01-01-00-00-00.txt")
+        inner.writestr("bugreport-test-2026-01-01-00-00-00.txt", DUMPSTATE)
+    return buffer.getvalue()
+
+
+def _wrapper_zip() -> zipfile.ZipFile:
+    buffer = io.BytesIO()
+    with zipfile.ZipFile(buffer, "w") as outer:
+        outer.writestr("app_logs/hilog.txt", "unrelated OEM log\n")
+        outer.writestr("bugreport-test-2026-01-01-00-00-00.zip", _inner_zip())
+    return zipfile.ZipFile(io.BytesIO(buffer.getvalue()))
+
+
+class TestCheckBugreportWrapper:
+    def test_nested_bugreport_is_used(self, tmp_path):
+        cmd = CmdAndroidCheckBugreport(results_path=str(tmp_path))
+        cmd.from_zip(_wrapper_zip())
+        module = cmd.modules[0](results_path=str(tmp_path))
+        cmd.module_init(module)
+        assert "main_entry.txt" in module.zip_files
+
+    def test_plain_bugreport_is_left_alone(self, tmp_path):
+        buffer = io.BytesIO()
+        with zipfile.ZipFile(buffer, "w") as archive:
+            archive.writestr("main_entry.txt", "bugreport.txt")
+            archive.writestr("bugreport.txt", DUMPSTATE)
+            archive.writestr("attachments/extra.zip", _inner_zip())
+        cmd = CmdAndroidCheckBugreport(results_path=str(tmp_path))
+        cmd.from_zip(zipfile.ZipFile(io.BytesIO(buffer.getvalue())))
+        module = cmd.modules[0](results_path=str(tmp_path))
+        cmd.module_init(module)
+        assert "attachments/extra.zip" in module.zip_files

tests/common/test_indicators.py

@@ -311,3 +311,31 @@ class TestIndicators:
         ind = Indicators(log=logging)
         ind.load_indicators_files([], load_default=False)
         assert ind.total_ioc_count == 9
+
+    def test_check_url_matches_w_prefixed_subdomain(self, tmp_path):
+        import json
+
+        stix_file = tmp_path / "w-domain.stix2"
+        stix_file.write_text(
+            json.dumps(
+                {
+                    "objects": [
+                        {
+                            "type": "indicator",
+                            "pattern": "[domain-name:value = 'web.evil.com']",
+                        }
+                    ]
+                }
+            ),
+            encoding="utf-8",
+        )
+        ind = Indicators(log=logging)
+        ind.load_indicators_files([str(stix_file)], load_default=False)
+
+        for url in (
+            "https://web.evil.com/path",
+            "https://www.web.evil.com/path",
+        ):
+            match = ind.check_url(url)
+            assert match is not None
+            assert match.ioc.value == "web.evil.com"

tests/common/test_url.py

@@ -22,3 +22,23 @@ def test_google_maps_url_is_not_shortened(url):
 
 def test_other_google_short_url_is_shortened():
     assert URL("https://goo.gl/example").check_if_shortened() is True
+
+
+@pytest.mark.parametrize(
+    "url, domain",
+    [
+        ("https://www.example.com/path", "example.com"),
+        # Only the whole "www." prefix comes off, not any leading "w" or "." character.
+        ("https://web.example.com", "web.example.com"),
+        ("https://wow.com", "wow.com"),
+        ("https://wired.com", "wired.com"),
+        ("https://www.wow.com", "wow.com"),
+    ],
+)
+def test_get_domain_strips_only_a_whole_www_prefix(url, domain):
+    assert URL(url).domain == domain
+
+
+def test_shortener_starting_with_w_is_detected():
+    assert URL("https://w3t.org/example").check_if_shortened() is True
+    assert URL("https://www.w3t.org/example").check_if_shortened() is True