elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill content is primarily instructional, providing a guide on how to interact with the ElevenLabs API using a specific command-line tool.
- [EXTERNAL_DOWNLOADS]: The skill references the
beltCLI and associated skills hosted byinference-shon GitHub. These are well-known resources within the platform ecosystem and are used for legitimate setup and configuration. - [COMMAND_EXECUTION]: The skill instructions involve executing the
belttool through a Bash environment. This is the intended primary function of the skill to facilitate audio generation. - [PROMPT_INJECTION]: The skill accepts user-provided text as input for the dialogue segments. While this constitutes an attack surface for indirect prompt injection (Category 8), the risk is minimal as the input is structured as JSON data and processed by a specialized text-to-speech inference service.
Audit Metadata