# pentest-agents-bug-bounty-framework

A bug bounty testing setup for autonomous vulnerability discovery. It coordinates 50 specialized agents, connects findings into exploit chains, and tracks targets in a local brain.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1300 installs · ★ 12
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/pentest-agents-bug-bounty-framework/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/pentest-agents-bug-bounty-framework

## What it does

This framework turns your coding assistant into an automated security hunter. It deploys 50 agents divided between coordinators (such as `chain-builder` or `hunt-orchestrator`) and specialized testers targeting SQLi, XSS, SSRF, or IDOR. The built-in brain tracks target endpoints persistently and combines isolated vulnerabilities into end-to-end exploit flows.

The tool ships with 26 slash commands, 19 CLI utilities, and 2 dedicated MCP servers. One server connects directly to platforms like HackerOne, Bugcrowd, and Intigriti to pull target scope and submit writeups. The other server looks up exploitation techniques across past bug reports using FAISS vector search, an SQLite database, or bundled payloads.

Platform integrations depend on explicit API credentials such as `HACKERONE_TOKEN`, and workspace scaffolding requires Python with `uv`. Running platform sync without these environment keys will immediately fail.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-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/pentest-agents-bug-bounty-framework/SKILL.md

## When to use it
- Chain isolated findings into A→B multi-stage exploits
- Sync program scope directly from HackerOne or Bugcrowd
- Evaluate bugs against the 7-Question Gate checklist
- Search past writeup databases for vulnerability techniques

## Example prompts
- Pull target scope with `/sync hackerone tesla` and examine the attack surface
- Validate the latest issue using `/validate` and build a chain via `/chain`
- Start an automated vulnerability loop for the target domain: `/autopilot tesla.com`

## Similar
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 57000 installs
- [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · 45400 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 54800 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 70200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 69 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