azure-ai-voicelive-ts

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests transcribed/streaming user text derived from user-provided audio (e.g., onConversationItemInputAudioTranscriptionCompleted and related delta handlers), which can be attacker-controlled via free-form user speech.