Skill Security Vetting

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 instruction-only vetting skill is internally consistent with its stated purpose: it asks the agent to inspect skill files and public GitHub metadata and does not request credentials or persistent privileges.

Purpose & Capability

The skill's name/description (a skill vetter) matches the instructions: it mandates reviewing files, checking sources, and querying public GitHub endpoints. It does not request unrelated binaries, credentials, or system configuration, which is proportionate for a vetting tool.

Instruction Scope

Instructions explicitly require reading "ALL files in the skill" and running curl against GitHub APIs/raw.githubusercontent for GitHub-hosted skills. This is appropriate for a vetter, but it grants broad read access to the skill package and requires network access to GitHub. The SKILL.md also instructs checking for reads of sensitive paths (e.g., ~/.ssh, ~/.aws) which is sensible as a red flag. Ensure the agent's runtime scope is limited to the skill's files and public network endpoints when following these steps.

Install Mechanism

No install spec or code files are present (instruction-only). Nothing is written to disk by the skill itself — lowest-risk installation footprint.

Credentials

The skill declares no required environment variables, credentials, or config paths. The instructions do not instruct reading env vars or secret files (they explicitly list those as red flags). This is proportionate.

Persistence & Privilege

always is false and there is no installation or self-modifying behavior. The skill does not request persistent presence or elevated privileges.

Assessment

This is a coherent, instruction-only vetter appropriate for pre-install checks. Before using it, ensure the agent executing these instructions is sandboxed so "read ALL files" is scoped to the skill package (not the whole filesystem). The vetting commands use public GitHub endpoints — avoid running them against private/restricted hosts unless you trust the network. Remember: the vetter reports red flags but does not itself verify semantics; for HIGH/EXTREME cases perform a manual human review and do not grant credentials or elevated rights to a skill based solely on this automated report.

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. 🔒🦀