ClawAudit verdict
agent-training-manual
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
This skill seems to provide a comprehensive training manual for new AI agents. It does not appear to use any capabilities in a way that would be considered risky or dangerous.
⚠ 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.
60
security
90
transparency
70
maintenance
Findings (2)
Pattern match critical
Accesses sensitive system files
04-tools.md · code · /etc/hosts
Pattern match medium
References agent memory files
02-workspace.md · code · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.