audio-language-models

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests arbitrary user-supplied or remote audio (e.g., transcribe_assemblyai(audio_url: str), transcribe_openai/transcribe_with_gemini accepting file paths, and the FastAPI /ws/voice endpoint receiving client audio) and then transcribes/uses that content in workflows, exposing the agent to untrusted third-party content that could carry indirect prompt injections.