ClawAudit verdict
agent-daily-retro
The skill defines standard operating procedures for daily retrospective analysis of AI agents.
⚠ 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.
Findings (4)
References agent memory files
INSTALL.md · code · MEMORY.md
References sudo — requests elevated privileges
INSTALL.md · prose · downgraded · sudo
Sets world-executable permissions
INSTALL.md · code · chmod 755
References webhook/callback URL
INSTALL.md · code · WEBHOOK_URL
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.