Skill Vetter 1.0.0

---
name: "skill-vetter-1.0.0"
description: "Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns."
priority: 0.5
version: "1.0.0"
imported-from: "hermes"
source-path: "hermes/skills/skill-vetter-1.0.0/SKILL.md"
---
# 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:
```bash
# 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"
```

## Registry/API Fallback and Monorepo Scope

If GitHub API quota or a registry resolver blocks inspection, do not skip review. Clone the repository over HTTPS into a temporary audit directory and enumerate tracked files locally:

```bash
git clone --depth 1 https://github.com/OWNER/REPO.git audit-repo
git -C audit-repo ls-files
```

For monorepos, audit both:

1. Every file inside the selected skill directory.
2. Repository-level manifests, install scripts, `postinstall` hooks, copiers, generators, or self-updaters that the chosen installation method will execute.

Risk belongs to the actual installation path, not only to `SKILL.md`. A clean skill folder can still be wrapped by an installer that writes extra skills, contacts a CDN, modifies host configuration, or deletes files. Prefer an installation method that copies only the reviewed skill when broader hooks are unnecessary.

After installation, verify the artifact independently by listing it in the target agent and loading its `SKILL.md` plus linked files. Do not treat a zero exit code as proof of success when command output reports an error.

## 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.* 🔒🦀