The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from npm, which is the official CLI tool for the Membrane platform. This is a standard and safe dependency for the skill's functionality.
[COMMAND_EXECUTION]: Employs the membrane CLI to manage connections and execute API actions. These commands are used as intended for service integration.
[SAFE]: Implements secure authentication workflows by using membrane login and membrane connect, which handle credentials externally rather than exposing them within the agent's instructions or local environment.
[SAFE]: Provides a surface for indirect prompt injection as it processes data from external action outputs. Ingestion point: output from membrane action run. Boundary markers: none. Capability inventory: CLI execution for action management. Sanitization: handled by the platform. This surface is inherent to the integration's purpose.

speakeasy