# claude-pentest-framework

claude-pentest-framework — a Claude skill that runs a structured pentest with 15 executor agents and 63 attack categories, asking the operator for approval before anything is exploited.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 261 installs · ★ 13 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/claude-pentest-framework/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/claude-pentest-framework

## What it does

Fifteen executor agents work under six domain coordinators, and the whole set covers 63 attack categories. Every agent follows the same routine: gather information, propose vectors, wait for a sign-off, then run. Nothing gets exploited on the agent's own initiative.

Each finding ships with proof. A working `poc.py`, its captured output in `poc_output.txt`, HTTP evidence and Playwright screenshots, all written to `outputs/{engagement}/` as JSON and markdown. Scope, attack profile and Kali settings sit in `.pentest-scope.json`, `.pentest-attacks.json` and `.pentest-mks.json` at the project root.

nmap, sqlmap, gobuster and Metasploit only answer through MCP-Kali-Server, deployed on a Kali Linux host and registered at an address like `http://192.168.1.10:5000`. Skip that host and you still get web-side checks, so network scanning takes preparation up front.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill claude-pentest-framework -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/claude-pentest-framework/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/claude-pentest-framework/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill claude-pentest-framework -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/claude-pentest-framework/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill claude-pentest-framework -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/claude-pentest-framework/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/claude-pentest-framework
```

2. **Manually: put the files in place**
- File: `.github/skills/claude-pentest-framework/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill claude-pentest-framework -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/security-skills --path skills/claude-pentest-framework
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/claude-pentest-framework/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill claude-pentest-framework -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/security-skills/tree/HEAD/skills/claude-pentest-framework/SKILL.md

## When to use it
- map a target's attack surface before sending real traffic
- pick attack categories that fit a web app or an API
- attach a runnable PoC and HTTP evidence to each finding
- route nmap and sqlmap calls to a separate Kali box
- close the engagement with a severity-bucketed summary

## Example prompts
- Run `/pentest:pentest` against `https://demo.testfire.net` with a 2 hour budget and Medium thoroughness
- Set the engagement scope with `/pentest:pentest-scope`: target, out-of-scope hosts, credentials
- Do recon and injection checks on the web application profile, but hold exploitation until I approve

## Similar
- [supabase-pentest](https://affpapa.org/en/nevibecode/skills/supabase-pentest.md) — skill · 748 installs
- [cairn-ai-pentest](https://affpapa.org/en/nevibecode/skills/cairn-ai-pentest.md) — skill · 378 installs
- [pentest-engagement-methodology](https://affpapa.org/en/nevibecode/skills/pentest-engagement-methodology.md) — skill · 356 installs
- [net-pentest](https://affpapa.org/en/nevibecode/skills/net-pentest.md) — skill · ★ 106 repo stars
- [web-pentest](https://affpapa.org/en/nevibecode/skills/web-pentest.md) — skill · 722 installs
- [pentest-checklist](https://affpapa.org/en/nevibecode/skills/pentest-checklist.md) — skill · 336 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 129 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
