Landingdang Skill Vetter 1 0 0

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 skill whose requested actions, lack of installs, and no secret requirements are coherent with its stated purpose as a skill-vetting checklist.

Purpose & Capability

Name/description match the content: SKILL.md is a vetting checklist that tells an agent how to review other skills. There are no declared env vars, binaries, or install steps that don't belong to a vetter.

Instruction Scope

Instructions legitimately ask the agent to read all files of the target skill and to use GitHub API/raw URLs to inspect repos. This grants broad read access to a skill's files (which is necessary for vetting). Be aware the quick-commands include remote fetches (curl) — fetching raw files is expected for vetting but the agent should not execute fetched code.

Install Mechanism

No install spec and no code files are included. Instruction-only skills present low install risk because nothing is written to disk by an installer.

Credentials

The skill declares no environment variables, credentials, or config paths. The SKILL.md warns against reading ~/.ssh, ~/.aws, etc., rather than instructing the agent to access them.

Persistence & Privilege

always is false and there are no configuration writes. disable-model-invocation is false (agent may call it autonomously) which is reasonable for a vetter; this autonomy is not combined with elevated privileges or extra credentials.

Assessment

This skill is a coherent, safe-to-read vetting checklist, but remember: (1) the vetter's commands include curl/raw GitHub fetches—do not automatically execute any fetched code; fetch only to inspect content. (2) When the vetter asks to 'read ALL files' it legitimately needs read access to the target skill's files — limit that access to the skill workspace, not system dirs. (3) For high-risk targets (credentials, installer scripts, packages), always require a human code review before installing. (4) If you want stricter safety, prevent autonomous invocation or run the vetter in a sandboxed environment and review its output manually.

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. 🔒🦀