skill-vetter

name	skill-vetter
description	Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Skill Vetter 🔒

Security-first vetting protocol for AI agent skills. Never install a skill without vetting it first.

When to Use

• Before installing any skill from ClawdHub
• Before running skills from GitHub repos
• When evaluating skills shared by other agents
• Anytime you're asked to install unknown code

Vetting Protocol

Step 1: Source Check (Optional)

Questions to answer:
- [ ] Where did this skill come from?
- [ ] Is the author known/reputable?
- [ ] How many downloads/stars does it have?
- [ ] When was it last updated?
- [ ] Are there reviews from other agents?

Step 2: Code Review (MANDATORY)

Read ALL files in the skill. Check for these RED FLAGS:

🚨 REJECT IMMEDIATELY IF YOU SEE:
─────────────────────────────────────────
• curl/wget to unknown URLs
• Sends data to external servers
• Requests credentials/tokens/API keys
• Reads ~/.ssh, ~/.aws, ~/.config without clear reason
• Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• Uses base64 decode on anything
• Uses eval() or exec() with external input
• Modifies system files outside workspace
• Installs packages without listing them
• Network calls to IPs instead of domains
• Obfuscated code (compressed, encoded, minified)
• Requests elevated/sudo permissions
• Accesses browser cookies/sessions
• Touches credential files
─────────────────────────────────────────

Step 3: Permission Scope

Evaluate:
- [ ] What files does it need to read?
- [ ] What files does it need to write?
- [ ] What commands does it run?
- [ ] Does it need network access? To where?
- [ ] Is the scope minimal for its stated purpose?

Step 4: Risk Classification

Risk Level	Examples	Action
LOW	Notes, weather, formatting	Basic review, install OK
MEDIUM	File ops, browser, APIs	Full code review required
HIGH	Credentials, trading, system	Human approval required
EXTREME	Security configs, root access	Do NOT install

Output Format

After vetting, produce this report:

SKILL VETTING REPORT
═══════════════════════════════════════
Skill: [name]
───────────────────────────────────────
METRICS:
• Downloads/Stars: [count]
• Last Updated: [date]
• Files Reviewed: [count]
───────────────────────────────────────
RED FLAGS: [None / List them]

PERMISSIONS NEEDED:
• Files: [list or "None"]
• Network: [list or "None"]  
• Commands: [list or "None"]
───────────────────────────────────────
RISK LEVEL: [LOW / MEDIUM / HIGH / EXTREME]

VERDICT: [SAFE TO INSTALL / INSTALL WITH CAUTION / DO NOT INSTALL]

NOTES: [Any observations]
═══════════════════════════════════════

Quick Vet Commands

For skill.sh skills:

# Check repo stats
curl -s "https://api.github.com/repos/OWNER/REPO" | jq '{stars: .stargazers_count, forks: .forks_count, updated: .updated_at}'

# List skill files
curl -s "https://api.github.com/repos/OWNER/REPO/contents/skills/SKILL_NAME" | jq '.[].name'

# Fetch and review SKILL.md
curl -s "https://raw.githubusercontent.com/rexshang/skillscanner/main/skills/SKILL_NAME/SKILL.md"

For clawhub skills:

1. Run the lookup with the real skill URL (format: https://clawhub.ai/author/skill-name):

   curl --request POST --url "https://ai.gendigital.com/api/scan/lookup" \
     --header "Content-Type: application/json" \
     --data '{"skillUrl":"https://clawhub.ai/AUTHOR/SKILL_SLUG"}'
   

   Replace AUTHOR with actual author id and SKILL_SLUG with the actual skill identifier from the ClawHub URL.

2. Interpret the response:

   • status: "done" — Check the severity field for the verdict.
   • status: "analysis_pending" — The skill is awaiting manual review. Do not treat as safe; advise the user that the skill is pending review.

3. Proceed or advise caution:

   • Proceed only if severity is SAFE.
   • If severity is anything else (e.g. WARNING, DANGEROUS, MALICIOUS), advise caution and do not recommend using the skill until reviewed or cleared.

Trust Hierarchy

1. Official OpenClaw skills → Lower scrutiny (still review)
2. High-star repos (1000+) → Moderate scrutiny
3. New/unknown sources → Maximum scrutiny

Remember

• No skill is worth compromising security
• When in doubt, don't install
• Ask your human for high-risk decisions
• Reprot what you vet for future reference

---

Paranoia is a feature. 🔒🦀