agent-red-teaming

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored free text from results.jsonl/JSONL records at runtime (via score_campaign.py: load_records reading and JSON-parsing each line, including the untrusted observed field), and it does not require prior selection of a specific item before ingest.