hrsd-chat-reply-recommendation

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

• Third-party content exposure detected (medium risk: 0.30). At runtime the workflow retrieves outsider-authored chat text by querying sys_cs_message.body for the active conversation (/api/now/table/sys_cs_message with sysparm_query=group=[conversation_sys_id]^ORDERBY...), then the LLM uses that content to generate reply recommendations.