text-to-speech
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill restricts the agent's execution environment by limiting 'allowed-tools' specifically to the
infshCLI tool. - [COMMAND_EXECUTION]: The skill provides standard command-line examples for interacting with the inference.sh platform, including login, app listing, and running speech generation tasks.
- [EXTERNAL_DOWNLOADS]: The documentation includes links to installation instructions and related skills hosted within the 'inference-sh' GitHub organization, which is the official source for this toolset.
- [PROMPT_INJECTION]: While the skill processes user-supplied text for speech generation, it uses structured JSON input (
--input '{"text": "..."}'), which is a recommended practice to separate data from instructions.
Audit Metadata