Caveat verdict

citedy-seo-agent

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill transmits user data (content) to external services (OpenAI's API) for SEO and content marketing purposes. While not directly malicious, it involves sharing potentially sensitive information with third-party services.

⚠ 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.

78
security
70
transparency
90
maintenance

Findings (3)

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

SKILL.md · prose · downgraded · You are now

Pattern match medium

References webhook/callback URL

SKILL.md · code · callback_url

Confirmed in code low

Data encoding/decoding

SKILL.md · code

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: CITEDY_API_KEY).

network_indata_encoding

Is this flag fair?

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