elevenlabs-dubbing

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

• Third-party content exposure detected (low risk: 0.10). The only outsider-controlled free text at runtime is the user-supplied --input JSON (e.g., audio URL and target_lang) to the localize pipeline commands (belt app run elevenlabs/dubbing/stt/infsh/caption-videos), and there is no required workflow step that automatically reads arbitrary outsider-authored text from a monitored external feed/queue without selecting a specific item.