π§ NeuroSploit v3.5.1
Autonomous, multi-model penetration-testing harness β Rust, CLI-only.
by Joas A Santos & Red Team Leaders
> β If this is useful, **star the repo** β it helps a lot.
>
> π **New here? Read the [full Tutorial & User Guide β](TUTORIAL.md)** β every mode, flag, config and example explained.
---
**NeuroSploit** turns a URL, a source repository, a running app, or a host/IP into
an autonomous security engagement. A Rust harness (`tokio`) drives a **pool of
LLMs** β via **API key** or local **subscription** (Claude Code / Codex / Gemini /
Grok) β recons the target, **intelligently selects only the agents that match the
discovered surface**, runs them in parallel, **chains** findings into deeper
impact, and **validates every claim by cross-model voting + tool-receipt
grounding** before reporting. It ships **329 markdown agents** and a **Mission
Control TUI**.
### Engagement modes
| Mode | Command | What it does |
|------|---------|-------------|
| **Black-box** | `neurosploit run ` | recon β select β exploit β vote β report |
| **White-box** | `neurosploit whitebox ` | source/SAST review (file:line evidence) |
| **Grey-box** | `neurosploit greybox --url ` | code review **+** live exploitation together |
| **Host/Infra** | `neurosploit host --creds creds.yaml` | Linux / Windows / Active Directory testing |
| **Mission Control** | `neurosploit tui ` | live TUI panels + composer during the run |
| **Interactive** | `neurosploit` | persistent REPL session (resumes per project) |
### Highlights
- π§ **POMDP belief + value-of-information** β the target is partially observable,
so findings aren't booleans: a property-graph **belief** carries probabilities,
and "scan more vs exploit now" falls out of belief entropy. The `may_assert`
gate is a **mathematical anti-hallucination rule** (don't claim exploitability
while the belief is diffuse).
- π§Ύ **Grounding** β hard rule: **no claim without a tool receipt** (raw tool
output, not paraphrase). Empirical for black-box, symbolic (`file:line`) for
white-box; ungrounded claims are demoted.
- π **Attack chaining** β 12 multi-stage chain agents (SQLiβRCEβLPE, SSRFβAWS
creds, uploadβLFIβRCEβLPE, default-credsβdomain, β¦); each stage proven before
advancing.
- πΊοΈ **Attack graph & kill chain** β findings mapped to OWASP / CWE / MITRE
ATT&CK / stage; rendered as a Mermaid graph in the report.
- β
**Cross-model validation** β a different model adjudicates each finding;
RL-weighted, recon-aware agent selection.
- π°οΈ **Mission Control TUI** β live header/feed/findings/targets panels + a
composer you can type in *while the run streams* (`summary`, `pause`, β¦).
- πΎ **Per-project memory** β `/.neurosploit/` keeps session, run history and
command history; the REPL **resumes** on reopen. No database required.
- πͺ **Token/cost telemetry**, per-agent attribution, graceful Ctrl-C β report or
discard, Typst/HTML/JSON/MD reports.
> This is the **slim, Rust-only** distribution (`neurosploit-rs/` + `agents_md/`).
> The earlier Python engine and web GUIs live on the older `v3.4.0` branch.
---
## π¦ Install (one line)
**Linux / macOS** (x64 & arm64):
```bash
curl -fsSL https://raw.githubusercontent.com/JoasASantos/NeuroSploit/main/setup.sh | bash
```
**Windows** (PowerShell, x64 & arm64):
```powershell
irm https://raw.githubusercontent.com/JoasASantos/NeuroSploit/main/install.ps1 | iex
```
### Supported platforms
| OS | x64 | arm64 |
|----|-----|-------|
| **Linux** (Kali recommended) | β
| β
|
| **macOS** | β
| β
(Apple Silicon) |
| **Windows** | β
| β
|
Pure Rust + stdlib, so it builds natively everywhere a stable Rust toolchain runs.
The installer auto-detects OS/arch and installs Rust if missing. On native Windows
use `install.ps1`; under WSL2 / Git Bash the `setup.sh` one-liner also works.
The installer auto-installs Rust if needed, clones the repo to `~/.neurosploit`,
builds the release binary, and links `neurosploit` into `~/.local/bin`. Re-run it
any time to update. Tweak with env vars: `NEUROSPLOIT_REF` (branch/tag),
`NEUROSPLOIT_DIR`, `PREFIX`.
Prefer to build by hand?
```bash
git clone https://github.com/JoasASantos/NeuroSploit && cd NeuroSploit/neurosploit-rs
cargo build --release # β target/release/neurosploit
```
## β‘ Quick start (60 seconds)
```bash
# easiest path β just run it; the interactive session asks everything:
neurosploit
# or one-liner (subscription login, no API key needed):
neurosploit run http://testphp.vulnweb.com/ --subscription --model anthropic:claude-opus-4-8 -v
# π° Mission Control TUI β live panels (header/feed/findings/targets) + a composer
# you can type in WHILE the run streams (summary Β· pause Β· errors Β· notes):
neurosploit tui http://testphp.vulnweb.com/ --subscription --model anthropic:claude-opus-4-8 --mcp
```
No login? Use an **API key** instead β see [Authentication](#authentication--run-via-api-key-or-subscription).
---
## Build
```bash
cd neurosploit-rs
cargo build --release # β target/release/neurosploit
```
Requires a Rust toolchain (`rustup`). **Recommended: run on Kali Linux** (or the
Kali Docker image) so the offensive tools the agents use are already present:
```bash
docker run -it --rm kalilinux/kali-rolling
apt update && apt install -y curl nmap ffuf nodejs npm
# rustscan (faster port scan): cargo install rustscan (or grab a release from GitHub)
```
The agents degrade gracefully: if `rustscan` isn't installed they use `nmap`; if
neither, they probe with `curl`. If a Playwright MCP browser is available they use
it for JS-heavy pages, otherwise they fall back to `curl`.
---
## Usage
Run with **no arguments** for an interactive wizard:
```bash
./target/release/neurosploit
```
Or drive it directly:
```bash
# Black-box β subscription (no API key), Opus, browser via Playwright if present, verbose
./target/release/neurosploit run http://testphp.vulnweb.com/ \
--subscription --model anthropic:claude-opus-4-8 --mcp -v
# Black-box β API keys, multi-model voting panel (1st finds, others adjudicate)
./target/release/neurosploit run http://testphp.vulnweb.com/ \
--model anthropic:claude-opus-4-8 --model openai:gpt-5.1 --vote-n 3
# White-box β clone a vulnerable app and review its source
git clone https://github.com/digininja/DVWA /tmp/DVWA
./target/release/neurosploit whitebox /tmp/DVWA \
--subscription --model anthropic:claude-opus-4-8 -v
# Offline pipeline self-test (no keys/login needed)
./target/release/neurosploit run http://testphp.vulnweb.com/ --offline
# Utilities
./target/release/neurosploit agents # library counts
./target/release/neurosploit models # providers & models
./target/release/neurosploit --help # full help with examples
```
### Options (`run` / `whitebox`)
| Flag | Meaning |
|------|---------|
| `--model provider:model` | Repeatable. First = primary; the rest fail over **and** form the voting jury. |
| `--subscription` | Use the local CLI login (Claude/Codex/Gemini/Grok) instead of an API key. |
| `--mcp` | Enable Playwright MCP (auto-provisioned via `npx`; backends without MCP use built-in tools). |
| `--vote-n N` | How many models must agree a finding is real (default 3 / 2 for whitebox). |
| `--max-agents N` | Cap agents run (`0` = all matching the recon). |
| `--offline` | Exercise the full pipeline without calling any model. |
| `-v, --verbose` | Log each agent as it launches, recon, and votes. |
### Authentication β run via API key *or* subscription
You can run NeuroSploit two ways. They're independent: pick per run.
#### 1) Via API (provider API key)
Export the key(s) for the providers in your model panel, then run **without**
`--subscription`. Any OpenAI-compatible provider works.
```bash
# pick one or more, depending on the models you select
export ANTHROPIC_API_KEY=sk-ant-... # anthropic:claude-*
export OPENAI_API_KEY=sk-... # openai:gpt-*
export GEMINI_API_KEY=AIza... # gemini:gemini-*
export XAI_API_KEY=xai-... # xai:grok-*
export NVIDIA_NIM_API_KEY=nvapi-... # nvidia_nim:*
export DEEPSEEK_API_KEY=... # deepseek:*
export MISTRAL_API_KEY=... # mistral:*
export DASHSCOPE_API_KEY=... # qwen:* (Alibaba DashScope)
export GROQ_API_KEY=... # groq:*
export TOGETHER_API_KEY=... # together:*
export OPENROUTER_API_KEY=... # openrouter:*
# ollama needs no key (local)
# then run via API (note: NO --subscription)
./target/release/neurosploit run http://testphp.vulnweb.com/ \
--model anthropic:claude-opus-4-8 --vote-n 3 -v
# multi-provider voting panel via API (1st finds, the others adjudicate)
./target/release/neurosploit run http://testphp.vulnweb.com/ \
--model anthropic:claude-opus-4-8 --model openai:gpt-5.1 --model gemini:gemini-2.5-pro
```
Or put the keys in a `.env` and source it (`cp .env.example .env`; edit; `set -a; . ./.env; set +a`).
**Provider β env var β endpoint** (all OpenAI-compatible):
| `--model` prefix | Env var | Base URL |
|------------------|---------|----------|
| `anthropic:` | `ANTHROPIC_API_KEY` | api.anthropic.com |
| `openai:` | `OPENAI_API_KEY` | api.openai.com |
| `gemini:` | `GEMINI_API_KEY` | generativelanguage.googleapis.com |
| `xai:` | `XAI_API_KEY` | api.x.ai |
| `nvidia_nim:` | `NVIDIA_NIM_API_KEY` | integrate.api.nvidia.com |
| `deepseek:` | `DEEPSEEK_API_KEY` | api.deepseek.com |
| `mistral:` | `MISTRAL_API_KEY` | api.mistral.ai |
| `qwen:` | `DASHSCOPE_API_KEY` | dashscope-intl.aliyuncs.com |
| `groq:` | `GROQ_API_KEY` | api.groq.com |
| `together:` | `TOGETHER_API_KEY` | api.together.xyz |
| `openrouter:` | `OPENROUTER_API_KEY` | openrouter.ai |
| `ollama:` | _(none)_ | localhost:11434 |
Run `./target/release/neurosploit models` for the full provider/model list.
#### 2) Via subscription (no API key)
`--subscription` drives your local agentic-CLI login instead of an API key β
install and log into one of the CLIs first:
| `--model` prefix | CLI used | Login |
|------------------|----------|-------|
| `anthropic:` | `claude` (Claude Code) | `claude` then `/login` |
| `openai:` | `codex` | `codex` login |
| `gemini:` | `gemini` | `gemini` login |
| `xai:` | `grok` | `grok` login |
```bash
./target/release/neurosploit run http://testphp.vulnweb.com/ \
--subscription --model anthropic:claude-opus-4-8 --mcp -v
```
---
## How it works
```
target ββΆ recon (curl/nmap/β¦) ββΆ INTELLIGENT agent selection (recon-aware)
ββΆ parallel exploitation ββΆ cross-model validation vote
ββΆ severity/score ββΆ report (HTML + Typst PDF) ββΆ RL reward update
```
Every run writes a self-contained folder `runs/ns--/`:
| File | Contents |
|------|----------|
| `status.json` | `running` β `complete` with a summary |
| `recon.json` / `recon.md` | mapped attack surface |
| `exploitation.md` | raw per-agent transcript |
| `findings.json` / `findings.md` | validated findings (reuse by other tools/AIs) |
| `report.html`, `report.typ`, `report.pdf` | final report (PDF via the Typst engine) |
A reinforcement-learning reward store (`data/rl_state_rs.json`) biases agent
selection on future runs.
## Agent library β `agents_md/` (303)
| Category | Count | Purpose |
|----------|-------|---------|
| `vulns/` | 196 | Exploit a specific vulnerability class |
| `recon/` | 12 | Information gathering / attack surface |
| `code/` | 78 | White-box source-code (SAST) review |
| `meta/` | 17 | Orchestrator, validator, scorers, reporter, RL |
Each agent is a self-contained markdown playbook (`## User Prompt` methodology +
`## System Prompt` strict anti-false-positive rules). Drop a new `.md` into the
matching folder and the harness picks it up.
---
## Safety
For **authorized** testing only. Agents are instructed to stay in scope, never run
destructive/DoS actions, and require proof-of-exploitation. You are responsible for
having permission for any target.
## Credits
**Joas A Santos** & **Red Team Leaders**.
## License
MIT.