vendor-privacy-audit

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests vendor-provided documentation/evidence (e.g., certifications, self-assessment questionnaires, incident log summaries, screenshots) during audit preparation/execution, which is outsider-authored free text at runtime; this content is then used to draft findings and reports in the agent’s LLM context.