elevenlabs-speech-engine

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text can enter the LLM context via the runtime onTranscript(transcript, signal, session) path: ElevenLabs sends user_transcript content that originates from the end-user (not the operating user), and the server forwards that transcript into the LLM input.