Skill Vetter Jarvis

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

This is an instruction-only vetting checklist whose requirements and instructions align with its stated purpose; nothing in the package requests unrelated credentials or installs code.

Purpose & Capability

Name and description match the content of SKILL.md: a checklist and commands for vetting other skills. No unrelated environment vars, binaries, or installs are requested.

Instruction Scope

SKILL.md stays on-topic: it instructs reviewing skill files, checking for obvious red flags, and gives GitHub API curl examples. It does not direct reading system files or exfiltrating data beyond the expected GitHub queries. The directive to "Read ALL files in the skill" is appropriate for a vetting tool (it targets the skill bundle, not arbitrary system files).

Install Mechanism

No install spec and no code files — the skill is instruction-only, which minimizes risk. Nothing is downloaded or executed by the skill itself.

Credentials

No required environment variables, credentials, or config paths are declared. The vetting instructions specifically mark credential requests and access to ~/.ssh, ~/.aws, etc., as red flags.

Persistence & Privilege

Flags use default (always:false) and model invocation is allowed (normal). There is no request for permanent presence or changes to other skills' configs. Note: because disable-model-invocation is false, an agent could invoke this skill autonomously — appropriate for a vetting helper but worth noting.

Assessment

This skill is an instruction-only vet checklist and appears coherent with its stated purpose. Before using it: 1) Ensure your agent environment has curl and jq if you want to run the example quick-commands (SKILL.md does not declare required binaries). 2) When following its advice, ensure the agent reads only the skill bundle files (not arbitrary home directories) — vetting should not grant the agent blanket access to your ~/.ssh, ~/.aws, or other sensitive paths. 3) The _meta.json version (1.0.1) differs from the SKILL.md header (1.0.0); this is minor but you may want to confirm the canonical version. 4) Do not let automated vetting be the sole decision-maker for high-risk skills — follow its checklist and require human review for medium/high/extreme findings.

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. 🔒🦀