eu-us-dpf-assessment

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests outsider-authored free text from the US importer’s privacy policy (a URL from the DPF listing) during the “Privacy Policy Review” step, which is not authored by the operating user and is read as prose into the agent context.