level-churn-analyzer

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path ingests outsider-authored free text via the user’s chat input that supplies analysis parameters (e.g., “User segment” can be “Custom” and asked to describe segment conditions), and the workflow then uses that user text to confirm/construct filters for downstream analysis.