Skill Vetter

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

Security Scan

The skill is an instruction-only vetting checklist whose requested actions and scope are consistent with its stated purpose and make no unexpected system or credential demands.

Purpose & Capability

Name/description claim to vet skills; SKILL.md only contains guidance and commands to fetch and inspect skill repos (e.g., GitHub API curl examples). It does not request unrelated credentials, binaries, or installs — this is proportionate for a vetting tool.

Instruction Scope

Instructions require reading all files of the target skill and optionally making network calls to GitHub (via curl examples). That is appropriate for vetting, but it assumes the agent has permission to fetch remote repos and to read the skill package being evaluated. The instructions do not tell the agent to read unrelated host secrets itself; they only flag those paths as items to check in target skills.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes installation risk because nothing is written to disk by the skill itself.

Credentials

The skill declares no required environment variables, credentials, or config paths. The checklist mentions sensitive paths as red flags for target skills, but does not request access to them for itself.

Persistence & Privilege

always is false and default autonomy is unchanged. The skill does not request persistent/system-wide changes or elevated privileges.

Assessment

This skill is a coherent, conservative vetting checklist and safe as an instruction-only helper. Before using it, ensure the agent has only the minimum permissions needed to fetch and inspect candidate skill repositories (network access and read access to the skill package). Remember: vetting a skill via these checks does not sandbox or prevent a vetted skill from later performing malicious actions at runtime — for higher-risk skills manually review code, prefer running them in isolated sandboxes, verify releases/tags on authoritative repos, and require human approval for any skill that requests credentials or system access.

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

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]
Source: [ClawdHub / GitHub / other]
Author: [username]
Version: [version]
───────────────────────────────────────
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 GitHub-hosted 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/OWNER/REPO/main/skills/SKILL_NAME/SKILL.md"

Trust Hierarchy

1. Official OpenClaw skills → Lower scrutiny (still review)
2. High-star repos (1000+) → Moderate scrutiny
3. Known authors → Moderate scrutiny
4. New/unknown sources → Maximum scrutiny
5. Skills requesting credentials → Human approval always

Remember

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

---

Paranoia is a feature. 🔒🦀