text-to-speech

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required workflow takes user-supplied free text in the text field and sends it to HeyGen’s POST https://api.heygen.com/v1/audio/text_to_speech for generation, meaning outsider-authored text is directly ingested by the LLM-adjacent generation step.