elevenlabs-dubbing-voice-conversion
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions are designed with safety in mind, explicitly directing the agent to refuse requests for unauthorized voice cloning or impersonation and providing safe alternatives for the user.- [EXTERNAL_DOWNLOADS]: The skill contains multiple references to official documentation and pricing pages on the ElevenLabs domain. These are informational links to a well-known service used for implementation guidance and do not involve the execution of untrusted code or scripts.- [DATA_EXPOSURE]: The skill operates as a guide for processing media through third-party APIs. It emphasizes the need for consent and rights verification before handling sensitive voice data. It also correctly identifies that certain services like Dubbing do not support zero-retention mode by default, prompting the agent to escalate privacy requirements appropriately.- [SAFE]: The skill establishes a clear boundary for the agent's behavior, focusing on localized production and transformation tasks while maintaining alignment with ethical standards and documented provider capabilities.
Audit Metadata