speech-to-text

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'belt' CLI tool to execute transcription and audio processing tasks. This is the primary intended function and is restricted to the 'belt' command via the YAML frontmatter.
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the vendor's official GitHub repository (github.com/inference-sh). It also suggests adding related skills using the 'npx skills add' command, which is part of the vendor's ecosystem.
  • [SAFE]: All external domains (inference.sh) and repositories (inference-sh) are associated with the skill's author. The operations described (login, running apps, processing audio URLs) are standard for a cloud-based speech-to-text service.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — speech-to-text