The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent and user to execute several shell commands using the membrane CLI to manage connections and run actions. These commands are part of the standard operating procedure for the Membrane integration platform.
[EXTERNAL_DOWNLOADS]: The instructions include installing the @membranehq/cli package from the public NPM registry. This is the official tool provided by the vendor (Membrane) for this integration and is a trusted resource.
[REMOTE_CODE_EXECUTION]: The skill utilizes the membrane action create and membrane action run commands. This allows for the dynamic generation and execution of logic on the Membrane platform based on user-defined intents. While this represents dynamic code execution, it is the primary purpose of the skill and is performed within the vendor's managed infrastructure.
[PROMPT_INJECTION]: The skill exhibits an indirect surface for prompt injection (Category 8) because it processes natural language 'intents' to create and execute actions. This is documented as a core feature of the integration, and the skill includes best practices to prefer managed actions over raw API calls.

niceboard