The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from npm, which is the official tool for the Membrane platform.
[COMMAND_EXECUTION]: Uses membrane CLI commands to manage connections and execute API actions. These are documented as standard operations for the integration.
[CREDENTIALS_UNSAFE]: Implements secure identity management by using Membrane's server-side connection system, explicitly advising against manual API key handling.
[PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the skill processes data from the external CATS API.
Ingestion points: Outputs from membrane action list, membrane action run, and membrane request commands.
Boundary markers: None identified in the provided instructions.
Capability inventory: Execution of CLI commands via subprocesses.
Sanitization: No specific sanitization logic is described for the API response data.

cats