Skill security

Skill suryast/free-ai-agent-skills/skill-security

Install

npx -y skills add suryast/free-ai-agent-skills --skill skill-security

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Security audit tool for AI agent skills. Scans for credential harvesting, code injection, network exfiltration, obfuscation. ALWAYS run before installing any new skill from external sources. Triggers on: new skill installation, skill audit, security scan, skill review, before loading external skill.

SKILL.md

3.0 KB, as published. Nobody here has run it

Skill Security Scanner

Security audit tool for AI agent skills. Run before installing any new skill.

Quick Audit

# Audit a skill directory
./skill-security/audit.sh /path/to/skill

# Audit all installed skills
./skill-security/audit-all.sh

What It Checks

Check	Risk Level	Pattern
Network Exfiltration	🚨 HIGH	`requests.`, `urllib`, `http.client`, `socket.`, `fetch(`, `axios`
Credential Harvesting	🚨 HIGH	`.ssh/`, `.aws/`, `pass` , `keyring`, `credential`, `secret`, `token` file reads
Code Injection	🚨 CRITICAL	`exec(`, `eval(`, `compile(`, `Function(`, `__import__`
Obfuscation	⚠️ MEDIUM	`base64.decode`, `atob`, encoded payloads
Env Dumping	⚠️ MEDIUM	`os.environ`, `process.env`, `getenv` bulk access
Subprocess Abuse	⚠️ MEDIUM	`subprocess.run`, `os.system`, `child_process` with credentials

Severity Levels

CRITICAL (🚨): Block installation, report to owner
HIGH (🔴): Requires manual review before use
MEDIUM (🟡): Note but allow if from trusted source
LOW (🟢): Informational only

Safe Skill Checklist

Before using any skill:

✅ Is it from a trusted source? (official OpenClaw, known publisher)
✅ Is the code readable (not obfuscated)?
✅ Does it document why it needs network/credential access?
✅ Does it scope file access to its own directory?
✅ Has it been audited by the community?

Integration with AGENTS.md

Add this to your workflow:

## Skill Installation Protocol

Before loading any new skill:
1. Run `./skill-security/audit.sh <skill-path>`
2. If CRITICAL/HIGH findings → STOP, alert the user
3. If MEDIUM findings → Review manually, proceed if justified
4. If CLEAN → Safe to use

Automatic Protection

The scanner creates a blocklist at ./blocklist.txt. Skills with CRITICAL findings are automatically added.

Manual Override

If a skill is flagged but you've verified it's safe:

echo "skill-name:verified:YYYY-MM-DD:reason" >> allowlist.txt

Premium Skills

Like this? Check out our premium skills at skillpacks.dev:

🛡️ Security Suite — Full PII scanning, secrets detection, prompt injection defense — $9.90
🧠 Structured Memory — Three-tier memory replacing flat MEMORY.md — $9.90
📋 Planning & Execution — Systematic task plans with batch execution — $9.90
💎 Bundle — all 3 for $24.90