review-monitor

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text (review titles/bodies) is fetched at runtime from NexScope Proxy endpoints (/api/v1/tools/linkfox/amazon/reviews/list or /amazon/usReviewsList), then ingested into the LLM context via review_monitor.py fields like classified_reviews/sample_reviews (which include title and text snippets) and are used to generate the final report.