voice-clone-tts
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references several external API endpoints for text-to-speech and voice cloning services, including OpenAI, Microsoft Azure, ElevenLabs, MiniMax, and Fish Audio. These are well-known technology providers and the references are documented neutrally for configuration purposes.
- [CREDENTIALS_SAFE]: The documentation for backend setup correctly uses placeholders (e.g., 'your_api_key') rather than hardcoding sensitive information, encouraging users to manage secrets safely.
- [DATA_EXPOSURE]: No evidence of unauthorized file access or data exfiltration. The network operations described are limited to sending text and audio samples to the user-configured official API endpoints of established services.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data for audio synthesis in the
synthesizeandbatchmodes. While this presents a theoretical surface for instructions embedded in input data, the skill's capabilities are restricted to audio generation, which does not pose a risk of command execution or system compromise. The risk is assessed as minimal and typical for TTS applications.
Audit Metadata