ClawAudit verdict

๐Ÿƒ coros

coros-skill

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

The skill retrieves running data from COROS, a sports tracking platform, for the user's training records, with no apparent malicious intent.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

78
security
70
transparency
70
maintenance

Findings (2)

Pattern match high

Possible hardcoded credential

main.py ยท prose ยท downgraded ยท token=")] filtered.append(f

Pattern match low

Python urllib.request โ€” network access

main.py ยท prose ยท downgraded ยท urllib.request

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API