temporal

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the runtime signal handler on_task_event_send (triggered by event/send), where user-provided message content (authored by someone other than the operating user) is typically incorporated into adk.providers.litellm.chat_completion inputs; this is not shown as sanitized/filtered in the required workflow path.