Caveat verdict
claw-score
The skill packages and submits agent configuration files for auditing, ensuring credentials are sanitized and data is transmitted to Atlas for analysis.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (3)
Pipe to python — executes piped content as Python code
submit.sh · prose · downgraded · | python3
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
References webhook/callback URL
submit.sh · prose · downgraded · WEBHOOK_URL
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.