text-to-speech

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a configuration and installation guide hosted on GitHub (raw.githubusercontent.com/inference-sh/skills/). This is a standard practice for CLI-based tools and targets a well-known service repository for its own ecosystem documentation.
  • [COMMAND_EXECUTION]: The skill provides examples of using the belt CLI tool to interact with various text-to-speech models. These commands are descriptive and intended for standard user interaction with the service.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to pass user-provided text to a TTS engine. While this represents a data ingestion surface, the risk is negligible as the data is converted to audio rather than interpreted as instructions by the agent.
  • [REMOTE_CODE_EXECUTION]: The skill suggests installing the CLI tool via npx skills add, which is the standard installation mechanism for this platform. It does not contain any arbitrary remote code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — text-to-speech