Skill Security Auditor

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this

151 stars 29 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mar-antaya/my-claude-skills --skill skill-security-auditor
Manual install
git clone --depth 1 https://github.com/mar-antaya/my-claude-skills.git /tmp/my-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/my-claude-skills/skill-security-auditor ~/.claude/skills/skill-security-auditor

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Skill Security Auditor

Scan and audit AI agent skills for security risks before installation. Produces a
clear **PASS / WARN / FAIL** verdict with findings and remediation guidance.

## Quick Start

```bash
# Audit a local skill directory
python3 scripts/skill_security_auditor.py /path/to/skill-name/

# Audit a skill from a git repo
python3 scripts/skill_security_auditor.py https://github.com/user/repo --skill skill-name

# Audit with strict mode (any WARN becomes FAIL)
python3 scripts/skill_security_auditor.py /path/to/skill-name/ --strict

# Output JSON report
python3 scripts/skill_security_auditor.py /path/to/skill-name/ --json
```

## What Gets Scanned

### 1. Code Execution Risks (Python/Bash Scripts)

Scans all `.py`, `.sh`, `.bash`, `.js`, `.ts` files for:

| Category | Patterns Detected | Severity |
|----------|-------------------|----------|
| **Command injection** | `os.system()`, `os.popen()`, `subprocess.call(shell=True)`, backtick execution | 🔴 CRITICAL |
| **Code execution** | `eval()`, `exec()`, `compile()`, `__import__()` | 🔴 CRITICAL |
| **Obfuscation** | base64-encoded payloads, `codecs.decode`, hex-encoded strings, `chr()` chains | 🔴 CRITICAL |
| **Network exfiltration** | `requests.post()`, `urllib.request`, `socket.connect()`, `httpx`, `aiohttp` | 🔴 CRITICAL |
| **Credential harvesting** | reads from `~/.ssh`, `~/.aws`, `~/.config`, env var extraction patterns | 🔴 CRITICAL |
Read the full skill on GitHub

Details

Skill name
skill-security-auditor
Path
skill-security-auditor/SKILL.md
Repo updated
16 March 2026
Copies
Found in 5 GitHub repos

FAQ

What does the Skill Security Auditor skill do?

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this

How do I install the Skill Security Auditor skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mar-antaya/my-claude-skills --skill skill-security-auditor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Skill Security Auditor popular?

It lives in mar-antaya/my-claude-skills, which has 151 GitHub stars and 29 forks, and is included in 2 curated skill lists.

Related skills

Tech Debt Tracker

151

mar-antaya/my-claude-skills

Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.

Software Development29

Security Threat Model

517

dotslashsimran/simcraft

Threat-model the user's own app from its real code. Draws the data flow (actors, trust boundaries, data stores, external services) as a Mermaid diagram, finds threats per element with STRIDE, ranks them by likelihood times impact, then proves each top risk with a local failing test, fixes it, and keeps the test as a regression test. Covers auth, IDOR and tenant isolation, injection, SSRF, secrets, CORS/CSRF, uploads, webhooks, dependencies, abuse, and LLM-app risks like prompt injection through tool output. Writes THREAT_MODEL.md. Use when the user says "threat model", "security review of my a

Security39

Security Review

335

zhukunpenglinyutong/ai-max

在添加认证、处理用户输入、处理密钥、创建 API 端点或实现支付/敏感功能时使用此 skill。提供全面的安全检查清单和模式。

Security37

Security Monitoring

581

claude-office-skills/skills

Automate security monitoring, threat detection, incident response, and compliance workflows

Security105

Better Auth Security Best Practices

230

better-auth/skills

Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth. Use when users need to secure their auth setup, prevent brute force attacks, or harden a Better Auth deployment.

SecurityIn 1 list38

K8S Security Policies

514

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.

Security146

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.