skill-audit-guardian

Audit dropped ClawHub skill ZIPs, classify risk (SAFE/CAUTION/REMOVE), auto-sort files, and generate a plain-English security dashboard.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "skill-audit-guardian" with this command: npx skills add howardkusumo/skill-audit-guardian

Skill Audit Guardian

Security helper for reviewing skill ZIPs before production install.

What it does

  1. Watches a drop folder for .zip files
  2. Audits each ZIP for suspicious patterns
  3. Scores and classifies into:
    • SAFE
    • CAUTION
    • REMOVE
  4. Auto-moves files into risk folders
  5. Generates a dashboard with plain-English reasoning per flagged line

Included scripts

  • scripts/skill-zip-audit.sh
    • One-shot ZIP auditor
  • scripts/skill-zip-watch.sh
    • Continuous watcher + auto-sorter
  • scripts/generate-skill-audit-pro.py
    • Dashboard generator (~/Desktop/skill-audit-pro.html)

Quick start

# One-shot audit
bash scripts/skill-zip-audit.sh ~/Desktop/skill-drop/example.zip

# Continuous mode (recommended)
bash scripts/skill-zip-watch.sh ~/Desktop/skill-drop

Folder output (watch mode)

  • ~/Desktop/skill-drop/safe
  • ~/Desktop/skill-drop/caution
  • ~/Desktop/skill-drop/remove
  • ~/Desktop/skill-drop/failed

Dashboard

open ~/Desktop/skill-audit-pro.html

Notes

  • This is heuristic scanning, not a full malware sandbox.
  • Always test CAUTION/REMOVE skills in isolated environment first.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Skill Guard

Security scanner for OpenClaw agent skills. Pre-install check via ClawHub page, local pattern scanning via read tool (zero exec), integrity verification. Use...

Registry SourceRecently Updated
2552Profile unavailable
Security

VibeSafe — Security Pre-Flight for AI Coding Agents

Security pre-flight for AI coding agents — plan libs, audit CVEs, certify, then code. Non-blocking in autonomous mode (ex-post report).

Registry SourceRecently Updated
1240Profile unavailable
Security

Skill Vetter — Security Audit for AI Skills

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...

Registry SourceRecently Updated
6830Profile unavailable
Security

Workflow Audit

Conduct a structured operational audit — identify friction points, map workflows, quantify waste, and produce a priority-ranked automation blueprint with ROI...

Registry SourceRecently Updated
1970Profile unavailable