text-to-speech

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the vendor's official GitHub repository (inference-sh/skills). This is a standard practice for tool setup.
  • [COMMAND_EXECUTION]: The skill is configured to use the belt CLI tool via Bash to perform text-to-speech tasks. This is the primary intended functionality of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text strings for conversion into audio. While this represents a data ingestion surface, it is consistent with the skill's purpose as a speech synthesis utility.
  • Ingestion points: User-provided text for the --input argument in belt app run commands.
  • Boundary markers: Not explicitly defined in the usage examples.
  • Capability inventory: Execution of belt CLI commands via Bash.
  • Sanitization: Relies on the underlying CLI and API for input processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 10:23 AM
Security Audit — agent-trust-hub — text-to-speech