n8n-debugging-official

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow includes calling get_execution(... includeData: true) and then “look at the failing node’s input/output,” which can contain outsider-authored free text from the user’s workflow inputs (e.g., messages/comments fetched from external systems) that the agent then reads into LLM context for diagnosis.