review-pg-patch

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text via search-pg-hackers by ingesting a saved thread JSON containing message bodies (scripts/review_memory.py ingest loads thread.get("messages") and stores message["body"] into the database), and later recall uses that stored text for full-text search.