# vulnhunter-security-scanner

The vulnhunter-security-scanner Claude Code skill searches source code for vulnerabilities and tests whether an attack could work. It activates on requests to scan a codebase or find exploitable bugs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 101 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/vulnhunter-security-scanner/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/vulnhunter-security-scanner

## What it does

The skill examines code from an attacker’s perspective. It follows paths from accessible entry points toward risky operations, then tries to disprove each candidate by looking for faulty assumptions or controls that would stop an attack.

The collection includes vulnerability hunting, test-driven fixes for confirmed issues, and a separate read-only fix check. It requires Claude Code CLI with access to Claude Opus and Python 3.12+. Git and an authenticated GitHub CLI are needed for the fix workflow; enrollment in the Anthropic Cyber Verification Program is recommended to avoid cyber safeguard blocks.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/vulnhunter-security-scanner
```

2. **Manually: put the files in place**
- File: `.github/skills/vulnhunter-security-scanner/SKILL.md`

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill vulnhunter-security-scanner -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/vulnhunter-security-scanner/SKILL.md

## When to use it
- find exploitable flaws in source code
- trace a route from an entry point to a risky operation
- discard findings blocked by security controls
- fix a confirmed issue with a security test
- validate a fix independently

## Example prompts
- Scan this codebase and find exploitable security bugs.
- Run `/vulnhunt` to inspect the code from an attacker’s perspective.
- Fix the confirmed vulnerability and verify it with tests.

## Similar
- [clawsec-scanner](https://affpapa.org/en/nevibecode/skills/clawsec-scanner.md) — skill · 195 installs
- [security-pen-testing](https://affpapa.org/en/nevibecode/skills/security-pen-testing.md) — skill · 834 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/security-audit.md) — skill · 673 installs
- [agentic-security](https://affpapa.org/en/nevibecode/plugins/agentic-security.md) — plugin · ★ 121 repo stars
- [security-scanner](https://affpapa.org/en/nevibecode/hooks/security-scanner.md) — hook · 2256 installs
- [agent-security-scanner-mcp](https://affpapa.org/en/nevibecode/mcp/agent-security-scanner-mcp.md) — MCP server · ★ 124 repo stars

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
