Claw Skill Vetter Pro

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 resources and behavior match its stated purpose; no code or credentials are requested, though provenance metadata is sparse and should be manually verified before trusting results.

Purpose & Capability

Name/description match the content: SKILL.md is a manual vetting checklist and provides GitHub API curl examples. It does not request credentials or install components, which is proportionate. Note: the _meta.json ownerId differs from the registry ownerId provided in the submission metadata and there's no homepage/source URL — that provenance mismatch is worth verifying before trusting this vetter.

Instruction Scope

Instructions are a human-style checklist (read all files, look for red flags, run provided curl queries). This stays within vetting scope, but it is high-level and manual — it relies on the agent/human having access to skill files and network. It does instruct 'Read ALL files in the skill', which is expected for a vetter but means the agent must be granted file access to the target skill only (avoid giving it broader system permissions).

Install Mechanism

No install spec and no code files — lowest install risk. Nothing will be written to disk by the skill itself.

Credentials

The skill requires no environment variables, credentials, or config paths; that is proportionate for an instruction-only vetting checklist.

Persistence & Privilege

always:false and default model invocation settings are used. The skill does not request persistent installation or elevated privileges.

Scan Findings in Context

[no-regex-findings] expected: The static scanner found no code to analyze because this is an instruction-only skill; that is expected for a checklist-style vetter.

Assessment

This skill is a manual vetting checklist and appears coherent and low-risk, but verify provenance before relying on it: confirm the author/owner, ensure the _meta.json ownerId matches the registry/source, and prefer running vetting actions in a sandbox or with access limited only to the target skill's files and network. Remember this tool is a checklist — it does not perform automated deep scanning, so perform human review for high-risk skills (credentials, system access, obfuscated code).

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

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. 🔒🦀