# vibe-pentest-ai-security-testing

Coordinates multi-agent security testing across web apps and APIs. Identifies injection flaws, authentication issues, and outputs DOCX or HTML reports.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 446 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/vibe-pentest-ai-security-testing/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/vibe-pentest-ai-security-testing

## What it does

The skill orchestrates security scanning across admin portals, endpoints, and web backends. Its workflow begins with technology fingerprinting, discovers parameters via the Katana crawler, and maps the attack perimeter before running tests.

Six parallel agents handle distinct security domains, covering authorization checks, injection attempts, and business logic flaws. The tool fails without Python 3.10+, Playwright Chromium binaries, and the Katana binary in place. Verified issues receive follow-up HTTP checks before creating HTML or DOCX summaries.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills vibe-pentest-ai-security-testing
```

2. **Manually: put the files in place**
- File: `.github/skills/vibe-pentest-ai-security-testing/SKILL.md`

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill vibe-pentest-ai-security-testing -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/vibe-pentest-ai-security-testing/SKILL.md

## When to use it
- map endpoints and parameters with the Katana crawler
- test web applications for business logic flaws and IDOR
- verify reported vulnerabilities with direct HTTP checks
- generate technical security findings in DOCX and HTML

## Example prompts
- Run an automated penetration test on our staging web application.
- Scan the admin endpoints for authentication flaws using vibe-pentest.
- Generate an HTML security assessment report based on recent scan findings.

## 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