Caveat verdict

learning-circle-client

thu-epiphany-client

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

A learning insight submission skill that posts structured notes to an organization Feishu document via a user-configured API token; it explicitly states no data is sent to third parties and all requests go only to the user-configured api_base.

⚠ 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.

68
security
70
transparency
70
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · token: "sk_fox_xxxxxxxxxxxxxxxx

Pattern match low

Node http/https module — low-level network access

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

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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