# skill-security-auditor

skill-security-auditor — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that scans agent skills before install. It detects prompt injection, dangerous code, credential harvesting and supply chain risks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 146 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/skill-security-auditor/SKILL.md
- Updated: 2026-11-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-skill-security-auditor

## What it does

Python files are checked for risky patterns: `os.system`, `subprocess` with `shell=True`, `eval`/`exec`, obfuscation via base64 or `chr()`, network exfiltration, reads from `~/.ssh` or `~/.aws`. Markdown, text and YAML get scanned for prompt injection: system-prompt overrides, zero-width characters, HTML comments with hidden instructions, and prompts that tell the assistant to conceal actions.

A separate checker looks at dependencies. Typosquatted package names (`reqeusts`), unpinned versions in `requirements*.txt` and `package.json`, inline `pip`/`npm install` calls. Pinned versions are not checked against CVE feeds; run `pip-audit`, `npm audit` or OSV-Scanner for that.

Each of the three scripts returns PASS / WARN / FAIL. PASS means "nothing obvious found", not "safe": the scanners match regexes line by line, and string building or helper indirection defeats them. After a PASS on an untrusted skill, read the code yourself.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill skill-security-auditor -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill skill-security-auditor -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill skill-security-auditor -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills engineering/skill-security-auditor/SKILL.md
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill skill-security-auditor -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/skill-security-auditor
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill skill-security-auditor -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/borghei/Claude-Skills/tree/HEAD/engineering/skill-security-auditor/SKILL.md

## When to use it
- scan a skill before installing it from an untrusted source
- catch hidden instructions in markdown and YAML
- detect reads of SSH keys or AWS credentials
- spot typosquatted packages and unpinned dependency versions
- gate skill installs in CI/CD

## Example prompts
- Scan `assets/sample_malicious_skill/` with all three checkers
- Run `python scripts/code_scanner.py skills/ --strict --json` and show HIGH findings only
- Check `requirements.txt` for unpinned versions and typosquatted package names

## Similar
- [skill-scanner](https://affpapa.org/en/nevibecode/skills/skill-scanner.md) — skill · 4200 installs
- [mcp-security-audit](https://affpapa.org/en/nevibecode/skills/mcp-security-audit.md) — skill · 1100 installs
- [dfyx-code-security-auditor](https://affpapa.org/en/nevibecode/skills/dfyx-code-security-auditor.md) — skill · 338 installs
- [ai-agent-security](https://affpapa.org/en/nevibecode/skills/ai-agent-security.md) — skill · 389 installs
- [repo-security-posture](https://affpapa.org/en/nevibecode/skills/repo-security-posture.md) — skill · 876 installs
- [llm-app-security](https://affpapa.org/en/nevibecode/skills/llm-app-security.md) — skill · 365 installs

## Other versions with the same name
- [skill-security-auditor · alirezarezvani](https://affpapa.org/en/nevibecode/skills/skill-security-auditor.md) — 785 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 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
