azure-ai-transcription-py

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts arbitrary remote audio URLs in begin_transcription (e.g., content_urls like "https://storage.example.com/audio.wav") and fetches/transcribes that external audio, so untrusted/public user-generated audio can be ingested and interpreted by the agent.