evidence-case-lab

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

• Third-party content exposure detected (medium risk: 0.30). In evidence_case_lab.py, the required runtime workflow ingests outsider-authored question text when --questions is provided (arbitrary JSON file) and passes each q_entry["question"] into _run_single() → EvidenceCaseRunner().run(question) for evaluation.