tao-run-inference-service

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

• Third-party content exposure detected (medium risk: 0.30). Source: tao-run-inference-service runtime path 6.2 Request format/6.0 Resolve which service receives this request sends outsider-authored user messages (including free-text prompt) as a JSON POST body to {BASE_URL}/v1/chat/completions, where BASE_URL comes from the service registry for the resolved job_id.