elevenlabs-tts

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via scripts/generate_voice.py read_text() reading --text, --text-file, or piped stdin, then sends that text to ElevenLabs in payload["text"] for /v1/text-to-speech/:voice_id generation.