Openclaw Skill Scanner

Security gate for OpenClaw AgentSkills. Scans folder/ClawHub skills with cisco-ai-defense/skill-scanner before installation. Supports manual scans, staged in...

This skill does what it says: it runs a scanner and can auto‑quarantine skills with High/Critical findings. Before enabling it, consider: 1) it executes third‑party code (the scanner from the GitHub repo and npm packages via npx/uv), so you must trust those upstream projects; 2) it will move (quarantine) user skill directories when High/Critical findings occur — back up your ~/.openclaw/skills if you want a safety copy; 3) it expects 'uv' and 'npx' (and optionally systemd --user) to be available — install and test those first; 4) review the scanner's code/behavior (cisco-ai-defense/skill-scanner and any npm packages used) if you need a higher assurance level. If you are uncomfortable with automated moves, run the scripts manually in a staging environment first.

Type: OpenClaw Skill Name: skill-scanner-guard Version: 1.0.2 This skill bundle is designed to enhance OpenClaw's security by acting as a 'skill scanner guard'. It orchestrates the use of an external `cisco-ai-defense/skill-scanner` tool to scan other OpenClaw skills for security issues, blocking or quarantining those with high-severity findings. All scripts (`auto_scan_user_skills.sh`, `clawhub_scan_install.sh`, `scan_and_add_skill.sh`, `scan_openclaw_skills.sh`) are transparently implemented, align with the stated defensive purpose, and include input sanitization for skill names and slugs. The `SKILL.md` instructions are clear and do not contain any prompt injection attempts. There is no evidence of intentional malicious behavior such as data exfiltration, unauthorized execution, or persistence mechanisms beyond its stated security function.