restack

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the public NPM registry. This is the official command-line tool for the platform provided by the vendor.
  • [COMMAND_EXECUTION]: Several shell commands are provided to interact with the Membrane CLI (membrane login, membrane connect, membrane action). These are standard operational commands for the platform's workflow.
  • [DATA_EXFILTRATION]: The skill explicitly instructs the agent to never ask for user secrets or API keys, instead utilizing the platform's server-side connection management. This is a positive security pattern that prevents credential harvesting and exposure within the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 11:09 AM
Security Audit — agent-trust-hub — restack