ClawAudit verdict
github-experiment-accuracy
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
Clones user-specified GitHub repos and runs model inference on user-provided data files to validate prediction accuracy; torch.load usage is for loading legitimate ML models from user-specified repos, consistent with stated purpose.
⚠ 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.
70
security
80
transparency
70
maintenance
Findings (1)
Pattern match critical
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_evaldir_traversal Is this flag fair?
Thanks — recorded.