speech-to-text

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to execute transcription and translation tasks via the inference.sh platform. This usage is restricted to tools authorized in the metadata and represents core intended functionality.\n- [EXTERNAL_DOWNLOADS]: The skill mentions installing the @agent-tools suite via npx and points to documentation and image resources on the inference.sh domain. These are trusted vendor resources and do not represent a security risk.\n- [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the skill processes external audio and video content. \n
  • Ingestion points: Media URLs (audio_url, video_url) provided to the infsh tool. \n
  • Boundary markers: None used in the shell command templates. \n
  • Capability inventory: Execution of authorized infsh CLI commands. \n
  • Sanitization: No explicit sanitization or filtering of transcribed text is performed within the skill code itself; safety relies on the underlying model's guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:52 AM