elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard integration wrapper for ElevenLabs TTS services provided via the inference.sh platform. It follows the least-privilege principle by restricting command execution to the
beltCLI tool. - [EXTERNAL_DOWNLOADS]: The skill references official installation instructions hosted on the vendor's GitHub repository (
inference-sh). These are legitimate resources required for the skill's operation. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for data ingestion where text is passed to the TTS engine via the
--inputflag. This is the primary intended functionality of the skill and no evidence of malicious redirection or bypass logic was found in the instructions.
Audit Metadata