Skill Defender

Scans installed OpenClaw skills for malicious patterns including prompt injection, credential theft, data exfiltration, obfuscated payloads, and backdoors. Use when installing new skills, after skill updates, or for periodic security scans. Runs deterministic pattern matching — fast, offline, no API cost.

kernel8901 Updated 7 repo stars

File contents

kernel8901/ai-agent-skills-classification commit 7007238a85

Frequently asked questions

npx get-skill add kernel8901/skill-defender