skill-vetter

Vet OpenClaw skills for permission scopes and suspicious patterns before installation.

Updated May 18, 2018
One-click install
npx skills add https://github.com/812lcl/dotfiles --skill skill-vetter-812lcl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-vetter
Source: https://github.com/812lcl/dotfiles/tree/main/.agents/skills/skill-vetter
Command: npx skills add https://github.com/812lcl/dotfiles --skill skill-vetter-812lcl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a security-focused vetting workflow to assess OpenClaw skills before installation, flagging risks and ensuring safe deployment.

Core Features & Use Cases

  • Legacy pre-install vetting module with a structured red-flag checklist that evaluates permissions, patterns, and suspicious instructions.
  • Audit-ready output that supports conservative install-or-block decisions and traceability.
  • Works when vetting skills from ClawHub, GitHub, or other sources, integrating manual review with automated checks.

Quick Start

Load the target skill's SKILL.md into the vetting module and generate the preliminary audit report.

Frequently Asked Questions about skill-vetter

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

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

You can vet OpenClaw skills by loading the target skill's SKILL.md into a vetting module to evaluate permission scopes, suspicious patterns, and red flags, generating a conservative audit report to support install-or-block decisions.

What security checks should I run before installing a skill from ClawHub or GitHub?

Security vetting before installation should apply structured checks covering permission scopes, suspicious instructions, and red-flag patterns to identify risks and ensure safe deployment from sources like ClawHub or GitHub.

How does a pre-install skill vetting audit work?

Pre-install skill vetting works by applying a structured red-flag checklist to evaluate permissions and patterns, combining automated checks with manual review to produce audit-ready output for traceability and conservative decision-making.

Can I use this vetting process for skills sourced from GitHub instead of ClawHub?

Yes, the vetting process works when assessing skills from ClawHub, GitHub, or other sources, applying the same structured permission scopes and red-flag pattern checks to aid install-or-block decisions across platforms.

What do I need to start auditing skill permissions and suspicious patterns?

To start auditing skill permissions, you need to load the target skill's SKILL.md file into the vetting module, which then evaluates the metadata to generate a preliminary audit report for review.