polygres-advisor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and reads the catalog, manifest, and selected documentation pages from the hosted Polygres library via web access.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill fetches behavior-shaping instructions and references from a hosted remote catalog (https://skills.polygres.com/...) under an unknown or third-party domain without verified strong first-party provenance.