ClawAudit verdict
skill-build-wizard
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill provides a guided workflow for building production-quality agent skills, and its content does not show any malicious or deceptive behavior.
⚠ 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.
90
security
60
transparency
70
maintenance
Permission integrity
Accesses agent memory/configuration files
agent_memory
Findings (1)
Pattern match medium
Instructs covert action — may act without user awareness
references/checklist-coding.md · prose · downgraded · silently
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.