技能检索
audit-code
Security-focused code review for hardcoded secrets, dangerous calls, and common vulnerabilities
duke-leto-test
Test skill to verify ClawHub publishing works correctly.
pincer
Security-first wrapper for installing agent skills. Scans for malware, prompt injection, and suspicious patterns before installation. Use instead of `clawhub install` for safer skill management.
expanso-log-sanitize
"Sanitize log entries by removing passwords, tokens, and sensitive patterns"
safety-checks
Verify before you trust — model pinning, fallbacks, and runtime safety validation
arc-security-mcp
AI-first security intelligence with LLM-powered intent analysis. 743+ findings from 361+ skill audits, 25 pattern rules, 22 attack classes.
aap-passport
Agent Attestation Protocol - The Reverse Turing Test. Verify AI agents, block humans.
token-alert
🚨 **Monitor session tokens and get alerts at 75%/90%/95%**
anti-injection-skill
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.