Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/deepgram-local-dev-loop/Gen Agent Trust Hub

deepgram-local-dev-loop

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • EXTERNAL_DOWNLOADS (SAFE): The skill uses curl to download a sample audio file from static.deepgram.com, which is a trusted domain for the service being integrated.
  • CREDENTIALS_UNSAFE (SAFE): Instructions include creating .env files, but use safe placeholder values like your-dev-api-key rather than hardcoded secrets.
  • COMMAND_EXECUTION (SAFE): Shell commands are restricted to standard project initialization tasks such as directory creation and package installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 05:27 AM