Caveat verdict

token-manager

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Monitors LLM API token usage and costs across providers; reads API key from env only to query the provider's own balance endpoint, which is the stated purpose with no exfiltration.

⚠ 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.

65
security
60
transparency
70
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key

Pattern match low

Node http/https module — low-level network access

scripts/manager.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

scripts/manager.js · prose · downgraded · process.env.MOONSHOT_API_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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