recipes
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a documentation resource for discovering official Deepgram code recipes.
- [EXTERNAL_DOWNLOADS]: References the official Deepgram GitHub repository for recipe content and provides instructions for installing official Deepgram SDK skills.
- [COMMAND_EXECUTION]: Mentions that code examples are designed to be executed as subprocesses during testing to verify output, which is a routine development practice.
- [CREDENTIALS_UNSAFE]: Adheres to security best practices by recommending the use of environment variables for managing the Deepgram API key rather than hardcoding credentials.
Audit Metadata