The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry. This is a vendor-owned tool required for the skill's operation.
[COMMAND_EXECUTION]: The skill executes various membrane CLI commands to manage authentication, connections, and service actions. These commands are part of the intended integration workflow.
[DATA_EXPOSURE]: The skill explicitly advises against asking users for API keys or tokens, instead utilizing a managed connection system that handles authentication server-side, reducing the risk of local credential exposure.
[PROMPT_INJECTION]: The skill identifies a surface for indirect instructions through the use of natural language intents and descriptions in commands like membrane action list and membrane action create. This is a documented feature of the platform and does not contain malicious patterns in the static instructions.

bouncer