deepgram-js-voice-agent
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill promotes secure credential management by instructing users to load the
DEEPGRAM_API_KEYfrom environment variables using thedotenvpackage rather than hardcoding it. - [SAFE]: All external URLs and API endpoints, such as
wss://agent.deepgram.comanddevelopers.deepgram.com, belong to the official vendor domain, which is appropriate for a skill authored by Deepgram. - [SAFE]: The command provided for adding additional skills (
npx skills add deepgram/skills) references the vendor's own official skill repository and represents standard platform functionality for this type of agent skill.
Audit Metadata