text-to-speech
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: User-provided text is interpolated into the
--inputargument for thebelt app runcommand inSKILL.md. - Boundary markers: The skill uses JSON formatting (e.g.,
{"text": "..."}) to encapsulate user input, which provides some structural separation but no explicit instructions to the model to ignore embedded commands. - Capability inventory: The skill utilizes the
beltCLI tool (Bash) to execute audio generation apps. - Sanitization: There is no evidence of input validation or sanitization for the text strings before they are sent to the TTS models.
- [EXTERNAL_DOWNLOADS]: The skill points to an external CLI installation script at
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdand recommends adding related skills vianpx. These resources are hosted by the vendor organization and are necessary for the skill's advertised functionality.
Audit Metadata