ClawAudit verdict
grill-skill
The skill uses dynamic_eval but in a controlled manner for its intended purpose of generating and iterating on caliper evals. 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 (3)
Recursive delete from root or home — destructive command
grill-skill.eval.yaml · prose · downgraded · rm -rf /
Instructs covert action — may act without user awareness
grill-skill.eval.yaml · prose · downgraded · silently
Popular HTTP library — network access
grill-skill.eval.yaml · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_eval Is this flag fair?
Thanks — recorded.