skill-vetter

Assess security and compliance risks in OpenClaw skills before installation.

Updated Jan 25, 2026
One-click install
npx skills add https://github.com/xfs96192/claude-config --skill skill-vetter-xfs96192
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-vetter
Source: https://github.com/xfs96192/claude-config/tree/main/skills/skill-vetter
Command: npx skills add https://github.com/xfs96192/claude-config --skill skill-vetter-xfs96192

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Core Features & Use Cases

  • Metadata validation: Ensure frontmatter includes name, version, and author.
  • Permission scope analysis: Evaluate each requested permission for necessity and risk.
  • Content review: Scan the SKILL.md body for red flags and potential prompt injection.
  • Audit-ready output: Produce a structured vetting report for install-or-block decisions.

Quick Start

Run the vetting protocol on a new skill before installation to decide whether to approve or block.

Frequently Asked Questions about skill-vetter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit OpenClaw skills for security risks before installing them?

To audit OpenClaw skills for security risks, run a vetting protocol that checks metadata validation, permission scope, and content for red flags to generate a structured risk assessment report.

What is permission scope analysis for skill vetting and compliance?

Permission scope analysis for skill vetting evaluates each requested permission within a skill to determine its necessity and potential risk, ensuring compliance before you approve the installation.

How do I check a ClawHub skill for prompt injection and suspicious patterns?

Check for prompt injection in ClawHub skills by performing a content review that scans the SKILL.md body for red flags, suspicious patterns, and potential security threats before installation.

When should I run a security audit on installed OpenClaw skills?

Run a security audit on installed OpenClaw skills during pre-install vetting for new additions and periodically for existing ones to continuously assess compliance risks and permission scopes.

Does the skill vetting process work with skills from sources other than ClawHub?

The skill vetting process works with skills from ClawHub, GitHub, and other sources by applying metadata validation, permission scope analysis, and content review to produce an audit-ready risk report.