Security-first skill auditing and quarantine for OpenClaw skills. Use when installing new skills, reviewing skills from unknown sources, scanning skills for prompt injection/exfiltration/supply-chain risks, or when a bot suspects a skill is malicious. Guides static + optional sandbox checks, quarantines suspicious skills, and produces an owner-action checklist (Delete / Report / Allow / Scan all).
SecurityClaw is a security-first skill + toolkit for OpenClaw that audits installed skills for: malicious behavior / exploit patterns prompt injection payloads embedded in docs secret exfiltration and unsafe tool usage risky install scripts / supply-chain issues When a suspicious or infected skill is detected, SecurityClaw’s workflow is: Quarantine the skill (move it out of the active skills directory) Generate a forensic report (what matched, where, why it’s risky) Notify the owner and await explicit instruction: Delete (remove quarantined files) Report (open an issue / publish IOCs) Allow (add to allowlist and restore) Scan all (deep scan all skills)