The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to manage connections and execute actions. These commands are specific to the platform's functionality and do not exhibit signs of arbitrary command injection or unauthorized system access.
[EXTERNAL_DOWNLOADS]: The skill references the installation of @membranehq/cli via npm and execution via npx. This package is the official command-line interface for the Membrane platform and is used as intended for service integration.
[CREDENTIALS_UNSAFE]: The skill explicitly advises against asking users for API keys or tokens, directing them instead to use the platform's managed connection system. This significantly reduces the risk of credential exposure.

munity