Caveat verdict
token-watch
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill tracks, analyzes, and optimizes token usage and costs. It provides guidelines for reducing token consumption and does not show 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. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
80
security
70
transparency
70
maintenance
Findings (1)
Pattern match high
Possible hardcoded credential
manifest.yaml · prose · downgraded · credential: "None — works locally with no API keys required
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.