elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'belt' CLI tool for audio generation. Access is restricted via the frontmatter 'allowed-tools' field, which ensures the agent can only execute commands prefixed with 'belt'.
- [EXTERNAL_DOWNLOADS]: The documentation points to installation instructions hosted on the author's official GitHub repository ('inference-sh'). This is standard practice for CLI-based skills and follows legitimate vendor resource patterns.
- [PROMPT_INJECTION]: The skill processes user-supplied text for speech synthesis. While this is a surface for potential indirect prompt injection (where the text might contain hidden instructions), it is the primary purpose of a text-to-speech skill and does not bypass the execution constraints imposed on the CLI tool.
Audit Metadata