LaunchKit · 2026
Back to Skills

azhua-skill-vetter

Security-first skill vetting for AI agents.

0
845 downloads
by @fatfingererr

Setup & Installation

openclaw skills install @fatfingererr/azhua-skill-vetter

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install azhua-skill-vetter

What This Skill Does

A structured vetting protocol for AI agent skills before installation. Scans for red flags like credential harvesting, obfuscated code, and unauthorized network calls. Produces a risk classification and a formatted report with a clear install verdict.

Replaces ad-hoc manual inspection with a repeatable checklist that catches common attack patterns and forces explicit risk classification before any code runs.

When to use it

  • Reviewing a ClawdHub skill before adding it to an agent
  • Auditing a GitHub-hosted skill shared by another agent
  • Checking whether a skill requests more permissions than its stated purpose requires
  • Evaluating skills from unknown or low-reputation authors
  • Producing a documented vetting record for team review before a high-risk install

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Vet this skill from GitHub before I install it

AGENT
  1. 1Fetch repo metadata to check stars, forks, and last updated date
  2. 2Read all files in the skill directory, starting with SKILL.md
  3. 3Scan code for red flags: external curl calls, credential file access, base64 decode, eval with external input
  4. 4Evaluate permission scope against the skill's stated purpose
  5. 5Classify risk level as LOW, MEDIUM, HIGH, or EXTREME
OUTPUT

SKILL VETTING REPORT with red flags listed, permissions catalogued, risk level assigned, and a SAFE TO INSTALL or DO NOT INSTALL verdict