speech-to-text

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to interface with the inference-sh platform using its official CLI tool, infsh. The allowed-tools configuration appropriately restricts the agent's command execution capability to only infsh commands, minimizing the risk of arbitrary command injection outside the intended scope.
  • [EXTERNAL_DOWNLOADS]: The documentation references npx skills add inference-sh/skills@agent-tools to install related tools. This points to the vendor's own repository and is a standard installation method for skills within this ecosystem.
  • [DATA_EXFILTRATION]: No indicators of unauthorized data movement were found. The skill processes external audio URLs which is consistent with its primary function of speech-to-text transcription.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:20 PM