skills/deepgram/skills/speech-to-text/Gen Agent Trust Hub

speech-to-text

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for Deepgram's Nova and Flux model families. It provides legitimate curl commands and WebSocket endpoint information for transcription services.
  • [COMMAND_EXECUTION]: Provides example curl commands for testing API endpoints. These commands are benign, intended for developer testing, and target official vendor domains (api.deepgram.com).
  • [CREDENTIALS_UNSAFE]: Appropriately instructs users to manage sensitive credentials using environment variables (DEEPGRAM_API_KEY) rather than hardcoding them, which follows security best practices.
  • [EXTERNAL_DOWNLOADS]: Includes links to official documentation and a sample audio file hosted on the vendor's own domains (deepgram.com, dpgr.am). All external references are within the vendor's known infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 05:11 PM