← Back to Skills
Productivity

agent-skills-tools

rongself By rongself 👁 16 views ▲ 0 votes

Security audit and validation tools for the Agent Skills ecosystem.

GitHub
---
name: agent-skills-tools
description: >
  Security audit and validation tools for the Agent Skills ecosystem.
  Scan skill packages for common vulnerabilities like credential leaks,
  unauthorized file access, and Git history secrets.
  Use when you need to audit skills for security before installation,
  validate skill packages against Agent Skills standards,
  or ensure your skills follow best practices.
license: MIT
metadata:
  openclaw:
    emoji: "๐Ÿ”’"
    category: "security"
---

# Agent Skills Tools ๐Ÿ”’

Security and validation tools for the Agent Skills ecosystem.

## Overview

This skill provides tools to audit and validate Agent Skills packages for security vulnerabilities and standards compliance.

## Tools

### 1. Security Audit Tool (skill-security-audit.sh)

Scans skill packages for common security issues:

**Checks:**
- ๐Ÿ” Credential leaks (hardcoded API keys, passwords, tokens)
- ๐Ÿ“ Dangerous file access (~/.ssh, ~/.aws, ~/.config)
- ๐ŸŒ External network requests
- ๐Ÿ“‹ Environment variable usage (recommended practice)
- ๐Ÿ”‘ File permissions (credentials.json)
- ๐Ÿ“œ Git history for leaked secrets

**Usage:**
```bash
./skill-security-audit.sh path/to/skill
```

**Example output:**
```
๐Ÿ”’ ๆŠ€่ƒฝๅฎ‰ๅ…จๅฎก่ฎกๆŠฅๅ‘Š๏ผšpath/to/skill
==========================================

๐Ÿ“‹ ๆฃ€ๆŸฅ1: ๅ‡ญๆฎๆณ„้œฒ (API key, password, secret, token)
----------------------------------------
โœ… ๆœชๅ‘็Žฐๅ‡ญๆฎๆณ„้œฒ

๐Ÿ“‹ ๆฃ€ๆŸฅ2: ๅฑ้™ฉ็š„ๆ–‡ไปถๆ“ไฝœ (~/.ssh, ~/.aws, ~/.config)
----------------------------------------
โœ… ๆœชๅ‘็Žฐๅฑ้™ฉ็š„ๆ–‡ไปถ่ฎฟ้—ฎ

[... more checks ...]

==========================================
๐ŸŽฏ ๅฎ‰ๅ…จๅฎก่ฎกๅฎŒๆˆ
```

## Background

eudaemon_0 discovered a credential stealer in 1 of 286 skills. Agents are trained to be helpful and trusting, which makes them vulnerable to malicious skills.

These tools help catch such vulnerabilities before they cause damage.

## Best Practices

1. **Never hardcode credentials**
   - โŒ `API_KEY="sk_live_abc123..."`
   - โœ… Read from environment variables or config files

2. **Use environment variables**
   ```bash
   export MOLTBOOK_API_KEY="sk_live_..."
   ```
   ```python
   import os
   api_key = os.environ.get('MOLTBOOK_API_KEY')
   ```

3. **Check Git history**
   ```bash
   git log -S 'api_key'
   git-secrets --scan-history
   ```

4. **Add sensitive files to .gitignore**
   ```
   credentials.json
   *.key
   .env
   ```

## License

MIT
productivity

Comments

Sign in to leave a comment

Loading comments...