Security audit
Security checks across malware telemetry and agentic risk
This skill analyzes OpenClaw session history to produce bounded learning suggestions, with disclosed storage and deletion controls, but users should review its learning/auto-apply language carefully.
Install only if you want local session-history analysis and persistent learning summaries. Use --agent for narrow scope, reserve --all for intentional broad review, periodically inspect or prune memory/learning, and do not let high-confidence suggestions change agent behavior without your review.
|-------|---------|----------| | 0.3 | Tentative | Suggested but not enforced | | 0.5 | Moderate | Applied when relevant | | 0.7 | Strong | Auto-approved | | 0.9 | Core behavior | Always apply | **Confidence increases when:**
65/65 vendors flagged this skill as clean.
No suspicious patterns detected.
