entity-compliance

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via --update --from-report when the user uploads a registered-agent compliance report (PDF/CSV/Excel) whose extracted body text is attacker-controlled by a third party, and via --sweep/other modes where the user pastes or provides information that may include outsider-authored content.