ClawAudit verdict
modelshow
A multi-model evaluation framework that queries models in parallel, anonymizes outputs with cryptographic randomization, and uses a judge sub-agent to rank responses — transparent blind evaluation tool with no suspicious data handling.
⚠ 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)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.