Caveat verdict

ouyi

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

API client for the ouyi AI model sending user questions and returning AI-generated answers; all calls go to the declared api.rcouyi.com endpoint with a user-supplied API key.

⚠ 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
40
transparency
70
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY = 'your-api-key-here

Pattern match low

Node http/https module — low-level network access

ouyi/scripts/ouyi-api.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

ouyi/scripts/ouyi-api.js · prose · downgraded · process.env.OUYI_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