skill-vetter

Use it when: you're about to install a skill from ClawHub, GitHub or another agent and want to know it's safe
It does: has the agent read every file of the skill against a list of red flags and rate its risk
You get: a vetting report: source, red flags, files, network and commands it needs, risk level and a verdict
Rejects: calls to unknown URLs, credential requests, base64 decoding, eval, obfuscated code, sudo, and reading ~/.ssh or the agent's memory files
Unlike: the SkillScan skill, which runs a Python scanner and blocks risky skills, it's a checklist the agent works through by reading the code

TLDR

A short security protocol for agents that install skills, aimed at the OpenClaw agent and its ClawHub skill registry. First the agent checks where the skill comes from: the author, downloads or stars, last update. Then it reads all of the skill's files for red flags: calls to unknown URLs or bare IP addresses, sending data out, asking for tokens or API keys, reading ~/.ssh, ~/.aws or the agent's own memory and identity files such as MEMORY.md and SOUL.md, base64 decoding, eval, obfuscated code, sudo, or installing packages it doesn't list. Any one of these means reject. A skill that passes is then weighed by what it reads, writes, runs and connects to, against what it claims to do, and sorted into four risk levels: low, such as notes or formatting (install); medium, such as files, browsers or APIs (full code review); high, such as credentials or trading (your approval); extreme, such as root access (don't install). Official skills and popular repos get a lighter review than unknown authors, but still a review. For skills on GitHub, it gives curl commands that check stars and fetch the files before installing.

Summarizes the skill at aca4fea.

openclaw skills install @spclaudehome/skill-vetter

ClawHub page · All skills from clawhub.ai/spclaudehome

Downloads: 273,769 on ClawHub, Sep 21, 2026
Downloads: 312,819 on Tencent SkillHub, Sep 21, 2026

Category	category:skill-tools category:security category:software-engineering Find, write, vet and route to other skills. Compliance, guardrails, skill vetting and browser fingerprinting. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:none Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	skill-security security

SKILL.md

From ClawHub, version 1.0.0. Checked daily, last changed Oct 20, 2026.

Frontmatter

name: skill-vetter
version: 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.

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

Official OpenClaw skills → Lower scrutiny (still review)
High-star repos (1000+) → Moderate scrutiny
Known authors → Moderate scrutiny
New/unknown sources → Maximum scrutiny
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. 🔒🦀