cookie-privacy-scan

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

• Third-party content exposure detected (high risk: 0.85). The skill navigates to a user-supplied URL at runtime and uses Playwright browser_evaluate/network log parsing to ingest the page’s own pre-consent cookie/storage state and third-party request URLs into the agent context, which is outsider-authored free text/content from the visited site.