data-manager-api-event-ingestion

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

• Third-party content exposure detected (high risk: 0.85). The required workflow instructs the agent to read Google’s API documentation at runtime (e.g., “Send events guide” and other developers.google.com pages), which is outsider-authored free text fetched from the public web and then ingested into the agent’s LLM context.