deepgram-js-audio-intelligence
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE]: The documentation demonstrates secure credential management by instructing users to load the Deepgram API key from environment variables using the dotenv package, preventing hardcoded secrets in code.
- [EXTERNAL_DOWNLOADS]: The skill references official Deepgram developer resources, OpenAPI/AsyncAPI specifications, and sample audio assets hosted on vendor-controlled domains (developers.deepgram.com and dpgr.am).
- [COMMAND_EXECUTION]: Includes a command to install supplemental vendor skills using 'npx skills add', which is a standard method for extending the agent's capabilities with authorized tools from the deepgram namespace.
Audit Metadata