fireberry

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI globally using 'npm install -g @membranehq/cli@latest'. This package belongs to the vendor's official scope on the NPM registry and is required for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill utilizes the 'membrane' CLI to perform operations such as authentication, connection management, and running CRM actions. These are standard administrative tasks for the tool and do not involve unsanitized user input or suspicious shell patterns.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by delegating authentication to the Membrane platform. It does not ask for or store API keys locally, instead using a 'membrane login' flow that handles tokens server-side.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 09:41 AM
Security Audit — agent-trust-hub — fireberry