The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the public npm registry. This is a standard installation for the vendor's platform tools.
[COMMAND_EXECUTION]: The skill uses the membrane command-line tool to perform operations such as logging in, connecting to Databox, and running actions. These commands are part of the intended functionality for the Databox integration.
[DYNAMIC_EXECUTION]: The skill includes a feature to create new actions dynamically using membrane action create. This allows the platform to generate integration logic based on a natural language description, which is a core feature of the Membrane platform.
[INDIRECT_PROMPT_INJECTION]: The skill processes data returned from Databox metrics and dashboards. This creates a surface where malicious content stored within the external Databox account could potentially influence the agent's behavior.
Ingestion points: Data enters the agent context through the output of membrane action run commands.
Boundary markers: None detected in the provided instructions.
Capability inventory: The skill can execute commands via the Membrane CLI, create new actions, and manage connections.
Sanitization: No explicit sanitization or filtering of the external data is described in the skill instructions.

databox