product-diagnosis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated content (e.g., Amplitude feedback via get_feedback_insights/get_feedback_mentions/get_feedback_comments, AI conversations via query_ai_sessions/get_ai_conversation, and Slack messages via slack_search_public) and instructs the agent to read and act on those quotes/conversations as evidence for diagnoses and next actions, so untrusted third-party content can materially influence behavior.