granola-auth

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The auth.js script uses child_process.exec to open the authorization URL in the system's default browser.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to mcp.granola.ai for OAuth discovery, client registration, and token exchange.
  • [CREDENTIALS_UNSAFE]: The skill manages OAuth tokens by writing them to a .env file in the current working directory and includes instructions to display masked tokens for user verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:49 AM