text-to-speech
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install the
beltCLI tool via a command and provides a link to installation documentation and scripts hosted on the inference-sh GitHub repository.- [COMMAND_EXECUTION]: The skill utilizes thebeltutility to perform operations related to AI inference, including authentication and running text-to-speech models with structured JSON input.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text for audio generation. - Ingestion points: User text is passed into the
textfield within the JSON input for thebelt app runcommand inSKILL.md. - Boundary markers: No specific delimiters or boundary markers are used to wrap the input text in the provided examples.
- Capability inventory: The skill is scoped to use the
beltCLI tool for interaction with the inference.sh API. - Sanitization: The skill instructions do not explicitly describe input sanitization or filtering mechanisms.
Audit Metadata