elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references setup instructions and documentation from the official inference-sh GitHub repository. These resources are provided by the service vendor and are legitimate for the skill's functionality.
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool within a restricted Bash environment (allowed-tools: Bash(belt *)), ensuring the agent can only execute specific, authorized commands for speech synthesis. - [PROMPT_INJECTION]: The skill processes user-supplied text to generate audio. It employs JSON-structured inputs as a data boundary, and because the resulting output is an audio resource, it does not pose a risk of returning malicious instructions back into the agent's execution flow.
- [SAFE]: Authentication is handled via a secure
belt loginworkflow, which avoids the exposure of sensitive API keys or credentials within the skill's instructions or environment variables.
Audit Metadata