google-meet
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [SAFE]: The skill utilizes the vendor-provided Membrane CLI (@membranehq/cli) for all interactions. Using official tooling from the author is a safe and expected practice.
- [SAFE]: The authentication process uses a browser-based OAuth flow managed by the Membrane platform, which avoids handling or storing sensitive API keys within the skill environment.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI from the public NPM registry, which is the official distribution channel for the vendor's tools.
- [COMMAND_EXECUTION]: The agent uses the
membranecommand to list, run, and manage Google Meet actions. These commands are executed within the scope of the user's authenticated session and follow the principle of least privilege. - [REMOTE_CODE_EXECUTION]: The skill includes the capability to create new integration actions dynamically via the Membrane platform. This is a core functionality of the service designed to simplify API integrations using natural language descriptions.
Audit Metadata