[opensourcedex]

NeuroSploit is a free, open source ai security & privacy project written in Rust and released under MIT. It has 1,477 GitHub stars, 351 forks and 2 open issues, and was last pushed 3 days ago. On this registry it ranks #24 of 46 tracked projects in AI Security & Privacy, with 5 head-to-head comparisons available.

What is NeuroSploit?

NeuroSploit is an open-source, MIT-licensed, CLI-first autonomous penetration-testing framework written in Rust that runs a full security engagement against a URL, source repository, host, or local artifact using a pool of language models, aimed at penetration testers, red teams, and security engineers who want the methodology handled by a harness rather than by step-by-step human driving.

What it is

NeuroSploit lives in the offensive-security tooling ecosystem, and its topic list places it among Kali Linux tools, ethical-hacking frameworks, and CTF utilities. It ships as a Rust binary named neurosploit under the MIT licence and accepts a URL, a source repository, a running application, or a host/IP address as its target. From there it conducts the engagement itself: reconnaissance, agent selection, parallel exploitation, verification, and reporting. Version 4.4.0 is described as an autonomous, multi-model penetration-testing harness, and it is CLI-first, with a web console and a TUI available as additional interfaces.

The specific thing it replaces is driving a single general-purpose model by hand. Rather than asking one LLM to "hack this", the project's premise is that the harness is the pentester and the model is not: a Rust engine built on tokio runs the methodology, picks the specialist agents that fit the discovered attack surface, runs them in parallel, re-sends every claim over the wire to confirm it reproduces, and has a second model adjudicate each finding before it reaches the report. That structure targets the familiar failure mode of model-driven testing, where findings are asserted but never verified. In NeuroSploit every claim needs a receipt, either raw tool output or a file:line reference, which is why the project argues it finds more and invents less than running a model directly.

Key capabilities

  • Eight engagement modes in one binary: neurosploit run for black-box recon-to-report, neurosploit whitebox for source review, neurosploit greybox --url for code review plus live exploitation, and neurosploit host --creds creds.yaml for Linux, Windows, Active Directory, and AWS/GCP/Azure targets.
  • Specialised testing modes: neurosploit aitest for jailbreaks, prompt injection, and OWASP LLM Top 10 / MCP issues; neurosploit mobile for reverse-engineering local artifacts with Ghidra, MobSF, and Frida; and neurosploit container for OCI image scanning with SBOM generation through trivy, grype, and syft.
  • Evidence-gated findings: each claim carries raw tool output or a file:line receipt, is re-sent by the harness to confirm reproducibility, and passes a cross-model vote before being reported.
  • Recon-driven agent selection, so only the agents matching the observed surface are executed, and they run in parallel.
  • Finding chaining, which combines individual results into demonstrated impact instead of reporting each in isolation.
  • Model flexibility through provider API keys or local subscriptions to Claude Code, Codex, Gemini, or Grok.
  • Three interfaces: the CLI, a browser console started with cd web && npm start on port 4173, and a live TUI via neurosploit tui with panels and a composer that accepts input mid-run.

Who uses it and how

  • Penetration testers and red team leads running black-box assessments of a web target, for example neurosploit run http://testphp.vulnweb.com/ --subscription --model anthropic:claude-opus-4-8 -v.
  • Application security engineers using white-box mode against a source repository to obtain file:line evidence, or grey-box mode to pair that review with live exploitation.
  • Infrastructure and cloud teams assessing Linux, Windows, and Active Directory hosts alongside AWS, GCP, and Azure estates through a creds.yaml credentials file.
  • AI security teams probing their own LLM applications for prompt injection and OWASP LLM Top 10 / MCP weaknesses with neurosploit aitest.
  • CTF players, learners working from a Kali Linux environment, and DevOps teams scanning OCI images and producing SBOMs.

Getting started

Install on Linux or macOS with curl -fsSL https://raw.githubusercontent.com/JoasASantos/NeuroSploit/main/setup.sh | bash, or on Windows with the install.ps1 PowerShell script; the installer adds Rust if it is missing, builds the release binary, and links neurosploit onto the PATH. Running neurosploit with no arguments opens an interactive session that asks for the target and options in plain language.

How it compares

No comparable or paid product is named in the facts supplied for this entry, so it stands alone in this registry within the AI Security & Privacy category as a harness-driven, autonomous penetration-testing framework rather than a single-purpose scanner. The project maintains its own BENCHMARK.md, described as an honest comparison, which is where measured contrasts should be sought.

When to use it — and when not to

A self-hoster must operate a Rust toolchain if building by hand, a Node.js environment for the web console, and persistent access to a model provider through either billed API keys or a local subscription, so the cost and the third-party dependency sit outside the harness. It is not the right pick for a team that cannot hold authorisation for offensive testing, or for anyone expecting a self-contained scanner that works with no model credentials at all. The honest weakness is that result quality is tied directly to the chosen models and provider, and the capability claims in the README are backed by pointers to BENCHMARK.md and TUTORIAL.md rather than by figures on the page itself.

project readme (upstream, from github) — read inline

🧠 NeuroSploit v4.4.0

Stars Forks Issues

Website Docs

Autonomous, multi-model penetration-testing harness — Rust, CLI-first.
by Joas A Santos & Red Team Leaders

What is NeuroSploit?

NeuroSploit is an autonomous penetration-testing tool. You point it at a target; it does the security assessment on its own and hands you a report — recon, exploitation, chaining findings into real impact, and validation, with no human driving each step.

The key idea: the harness is the pentester, not the model. Instead of asking one LLM to "hack this", a Rust engine runs the methodology — it picks the right specialist agents for what it finds, runs them in parallel, re-sends every claim over the wire to confirm it's real, and has a second model check each finding before it's reported. The LLMs are the hands; the harness is the discipline that keeps them honest. That's why it finds more and invents less than running a model directly.

It's CLI-first (with a web console and a TUI), open source (MIT), and runs on your own API keys or a local subscription — nothing about your targets leaves your machine unless you send it.

Give NeuroSploit a URL, a source repo, a running app, or a host/IP. A Rust harness (tokio) drives a pool of LLMs — via API key or local subscription (Claude Code / Codex / Gemini / Grok) — and runs the whole engagement for you:

recon ─▶ pick only the agents that fit the surface ─▶ exploit in parallel
      ─▶ wire-check every claim ─▶ cross-model vote ─▶ chain into deeper impact ─▶ report

It won't invent findings: every claim needs a receipt (raw tool output or a file:line), is re-sent by the harness itself to confirm it reproduces, and is adjudicated by a second model before it reaches the report.

⭐ Useful? Star the repo. 🌐 Website & live docs: neurosploitai.github.io · Tutorial & Guide 📖 Deep dive: TUTORIAL.md · changelog: RELEASE.md · honest comparison: BENCHMARK.md

Install

Linux / macOS (x64 & arm64):

curl -fsSL https://raw.githubusercontent.com/JoasASantos/NeuroSploit/main/setup.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/JoasASantos/NeuroSploit/main/install.ps1 | iex

The installer sets up Rust if missing, builds the release binary, and links neurosploit onto your PATH. Build by hand instead:

git clone https://github.com/JoasASantos/NeuroSploit && cd NeuroSploit/neurosploit-rs
cargo build --release      # → target/release/neurosploit

Quick start

# just run it — the interactive session asks everything, in plain language:
neurosploit

# black-box, subscription login (no API key):
neurosploit run http://testphp.vulnweb.com/ --subscription --model anthropic:claude-opus-4-8 -v

# white-box — review a source repo (file:line evidence):
neurosploit whitebox /path/to/repo --subscription --model anthropic:claude-opus-4-8 -v

# web console — a browser UI over the same CLI:
cd web && npm start     # → http://localhost:4173

No subscription? Use an API key for any provider instead — see TUTORIAL.md.

Modes

Mode Command What it does
Black-box neurosploit run recon → select → exploit → vote → 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 / AD + cloud (AWS/GCP/Azure)
AI / LLM neurosploit aitest jailbreaks, prompt injection, OWASP LLM Top 10 / MCP
Mobile / Binary neurosploit mobile RE a local artifact (Ghidra / MobSF / Frida)
Container neurosploit container OCI image scan + SBOM (trivy/grype/syft)
Mission Control neurosploit tui live TUI panels + a composer you type in mid-run

What makes it different

  • The harness is the pentester. Agent selection is recon-driven; findings chain (reduce a foothold to a primitive — exec / read / write / SSRF / identity / secret — then pivot), each stage proven and non-destructive.
  • Wire-bound evidence — every reported exchange is re-sent through a scope-guarded replay engine and checked against recorded traffic. A claim the wire contradicts can't stand as confirmed.
  • Attack knowledge graph (Neo4j optional) — the run is a typed graph of hosts, services, findings, credentials and impact, spanning web and internal network. It directs the next move during the run and is written to graph/ even without a database.
  • Deterministic validation — per-CWE validators judge the measured request/response bytes, not the model's prose. Grounding gate, POMDP belief and an anti-hallucination check demote anything the evidence doesn't support.
  • Secrets never leak the report — credentials the agents observe become $SECRET_n in every human-facing report; raw values stay in the run's vault for re-testing only.
  • Execution resilience — classified error handling (7 error types), exponential backoff (5 retries, 2s–90s), crash-state salvage (partial findings survive agent failure), agent lifecycle nudge (3 retries with simplified prompts), progressive budget warnings (70/85/95%), and run snapshot/resume so interrupted engagements pick up where they left off.
  • LLM-powered dedup — deterministic fast-path for exact matches, plus a semantic LLM judge for findings with different wording but the same root cause.
  • 486 markdown agents across web, code (SAST), AI, infra/AD/cloud, chains and recon — each a self-contained playbook you can read, edit or add to.
  • Run via API key or subscription, 19 providers, including local & CPU-only (ollama: / llamacpp:) with no data leaving the host.

Web console

cd web && npm start     # → http://localhost:4173

A browser UI that drives the same CLI — no second engine. Launch and watch a run live, then per finding:

  • Attack graph — host → service → finding → credential → impact, every edge marked confirmed / needs-validation / hypothesis, ordered by kill-chain stage.
  • Wire evidence — the real request/response pairs behind a finding (baseline vs. attack, the identity pair, matrix probes, the oracle), each tagged with its wire provenance — the proof as bytes, not prose.
  • Re-test one finding — re-run its proof through the replay engine; the dated history shows a finding drift to "gone" over time.
  • Transcript viewer — any agent's run, split into navigable blocks; search spans every agent.
  • Chains, dependency todolist, recorded traffic, deliverables, PDF export.

What a run leaves behind

Every run is a self-contained folder, runs/ns--/:

File Contents
report.html · report.pdf · report.md the report (PDF via Typst), secrets redacted
findings.json / findings.md validated findings (raw, for tools & re-testing)
report.sarif SARIF 2.1.0 for CI code-scanning
graph/ attack chains, dependency todolist, Cypher + JSON export
recon.json · exploitation.md · traces/ surface, transcript, per-agent traces
pocs/ · evidence/ runnable PoCs and proof screenshots

Integrations

GitHub / GitLab PR review gate (neurosploit pr --fail-on critical), @neurosploit mention bot, one Jira card per finding, MCP server (neurosploit mcp), compliance mapping (PCI-DSS / HIPAA / SOC 2 / GDPR). See TUTORIAL.md.

Safety

For authorized testing only. Agents stay in scope, never run destructive / DoS actions, and require proof of exploitation. You are responsible for having permission for every target.

Credits & license

Joas A Santos & Red Team Leaders — MIT.

This is the slim, Rust-only distribution (neurosploit-rs/ + agents_md/). The older Python engine and web GUIs live on the v3.4.0 branch.

Frequently asked questions

Is NeuroSploit free to use?

NeuroSploit is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does NeuroSploit do?

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations.

What is NeuroSploit written in?

NeuroSploit is primarily written in Rust. Its source is publicly available at https://github.com/JoasASantos/NeuroSploit, and it has 1,477 GitHub stars.