ClawAudit verdict
openclaw-auto-training-skill
45
🟠 Risky
Significant concerns — only install if you understand the risks
The skill evaluates and improves the agent autonomously. While the purpose is legitimate, the use of dynamic_eval could potentially lead to security issues if not carefully managed.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
100
security
100
transparency
90
maintenance
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_eval Is this flag fair?
Thanks — recorded.