The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the npm registry. This is the official command-line interface provided by the vendor (Membrane) and is required for the skill to operate.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform legitimate operations such as authentication, action discovery, and workflow execution. These commands are localized to the Membrane environment and do not pose a security risk to the host system.
[SAFE]: Authentication is handled using managed connections (OAuth/Personal Access Tokens managed server-side by Membrane), which prevents sensitive credentials like API keys from being exposed in the agent's context or local environment.
[SAFE]: The instructions promote secure data handling by advising the agent to let the platform manage the full authentication lifecycle server-side.

boloforms