risk-mitigation

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow only reads a user-provided JSON config file passed via --config and processes its free-text fields like each risk name and current_mitigation with json.load, so outsider-authored free text can be ingested into the LLM-relevant workflow without selecting a specific trusted item.