fireflies

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is an official tool provided by the vendor (Membrane).
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with the membrane CLI for logging in, managing connections, and executing actions. These are standard operations for this platform integration.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates secure credential handling by using a delegated authentication flow (membrane login) and specifically advising users never to handle API keys or tokens directly within the agent context.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data access or exfiltration was found. Network operations are limited to the intended functionality of the Membrane and Fireflies APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 07:04 AM
Security Audit — agent-trust-hub — fireflies