text-to-speech
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and installation guidelines from the official inference.sh GitHub repository and platform domains.
- [COMMAND_EXECUTION]: Invokes the belt CLI tool to interact with text-to-speech models. The execution environment is appropriately restricted to the belt command via the allowed-tools configuration in the YAML frontmatter.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing user-provided text into audio.
- Ingestion points: User-supplied strings are passed to the --input argument of the belt command in SKILL.md.
- Boundary markers: Input is structured within JSON objects passed to the CLI tool.
- Capability inventory: The skill is restricted to the belt CLI tool.
- Sanitization: Input is handled by the underlying inference.sh platform for speech synthesis.
Audit Metadata