Skill Vetter.Bak

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's stated purpose (vetting other skills) matches its instructions, but there are small inconsistencies and operational assumptions (missing declared binaries, mismatched metadata) that should be clarified before trusting it automatically.

Purpose & Capability

The name/description (skill vetter) align with the SKILL.md: it only describes manual/automated checks and GitHub queries. However the SKILL.md uses curl and jq examples but the skill metadata declares no required binaries — a mismatch that could cause runtime failures or unexpected behavior.

Instruction Scope

Instructions focus on reviewing skill files and checking repository metadata. They do not instruct the agent to access unrelated system credentials or config files. They do include 'Read ALL files in the skill' (which is appropriate) and example commands that perform network calls to GitHub/raw.githubusercontent; the agent will need network access to run those examples.

Install Mechanism

Instruction-only skill with no install spec and no code files — low disk-write risk. There is no download/install behavior declared in the skill itself.

Credentials

The skill requests no environment variables or credentials, which is appropriate. It does assume availability of networking and CLI tools (curl, jq) but does not declare them. No sensitive secrets are requested.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent presence or elevated privileges. Nothing in SKILL.md instructs it to modify other skills or system-wide configs.

What to consider before installing

This skill is fundamentally coherent: it describes how to vet other skills and gives concrete checks and example commands. Before installing/using it, verify two small issues: (1) the SKILL.md examples use curl and jq but the registry metadata doesn't list required binaries — ensure your agent environment actually has those tools or update the skill to declare them; (2) the _meta.json ownerId/publishedAt differ from the registry metadata shown — confirm the skill author and source to avoid supply-chain confusion. Also remember the vetter will perform network calls (GitHub/raw.githubusercontent) when run — treat network access and fetched content as untrusted and do a manual review for high-risk skills.

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. 🔒🦀