configuring-ai-agents

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for an AI import/guardrail ingests outsider-authored free text that comes from monitored in-flight records and maps them into the agent’s text (defaulting to the whole un-mapped record as record), where the LLM processes it per configured instructions.