ClawAudit verdict
daily-questions
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill asks users questions to build understanding and improve agent behavior, with a configurable schedule and multiple choice answers.
⚠ 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.
98
security
80
transparency
70
maintenance
Findings (1)
Pattern match low
Popular HTTP library — network access
references/example-questions.md · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.