deepgram-python-conversational-stt

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several official documentation URLs from the developers.deepgram.com domain. These are used to provide the user with API references, quickstart guides, and product documentation.
  • [COMMAND_EXECUTION]: The skill suggests a command (npx skills add deepgram/skills) to install supplementary product knowledge. This command targets the vendor's official skill repository and is a standard procedure for extending agent capabilities.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates safe credential handling by using python-dotenv to load the DEEPGRAM_API_KEY from an environment variable rather than hardcoding it in the script.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill correctly instructs the agent to send audio data to the official Deepgram API endpoints using the provided SDK.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 01:46 PM