missav

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

• Third-party content exposure detected (low risk: 0.10). The workflow browses and extracts search listings and detail-page plot descriptions from missav.ws, which are outsider-authored web pages fetched dynamically via search queries and selected links.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency on missav.ws is evidenced through runtime URLs fetched via agent-browser, but the first-party publisher provenance is unknown or arbitrary, resulting in a high tier.