Skip to content
LoginGet started

OpenClaw only

Skill Vetter

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.

  • Pass
  • Security
  • Version 1.0.0
Publisher
spclaudehome
Runs on
OpenClaw only
Updated
September 16, 2026
Downloads on ClawHub
274.6k
Installs on ClawHub
12.2k
Stars
1.3k
Category
Security View on ClawHub

Security review

PassChecked on September 26, 2026

This skill is a security checklist for reviewing other skills and does not contain hidden execution, persistence, credential use, or destructive behavior.

The review is ClawHub’s, shown here as published. Diali does not edit it. Read the full audit on ClawHub

What it needs before the first run

Nothing to configure. It runs as soon as it is installed.

Install it on your Diali agent

  1. Open Skills in the dashboard

    Every plan includes the catalog. Search for the skill by name.

  2. Read the review, then install

    The verdict and summary above are shown again on the install screen. Pick the agent it goes on.

  3. Give it what it needs, then use it

    If the skill asks for credentials or settings, the dashboard collects them. The skill then runs inside the agent’s own sandbox.

Build your agentSee pricing

From the skill’s README

Written by the publisher and shown as published on ClawHub.

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

code
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:

code
🚨 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

code
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:

code
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"

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.* 🔒🦀

Get started

Give a skill an agent to run on

Every plan includes the skills catalog, every channel and every connector. Build an agent and install your first skill from the dashboard.

Build your agentSee pricing