ClawAudit verdict
butler-mode
The butler mode skill acts as a manager that delegates work to teammate agents. It does not perform any direct work and only uses tools for understanding context and coordination. There is no evidence of malicious 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.
Findings (1)
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · You are now
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Is this flag fair?
Thanks — recorded.