goal

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow only mandates loading first-party doctrine/flow variants and uses internal in-chat execution context plus optional /trackers (read-only), but it does not specify ingesting arbitrary outsider-authored free text into the LLM without explicitly selecting specific items; therefore there is no direct poisonable queue/feed described.