The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the official @membranehq/cli package from the npm registry to manage integrations.
[COMMAND_EXECUTION]: Utilizes shell commands via the membrane CLI for authentication, connection management, and running actions.
[DATA_EXFILTRATION]: Performs network requests to Membrane's infrastructure for authentication and API orchestration. This is a core part of the skill's functionality and uses the vendor's managed authentication system.
[PROMPT_INJECTION]: The membrane action create and membrane action list commands ingest natural language descriptions. This represents a surface for indirect prompt injection (Category 8), though the risk is mitigated by the platform's internal processing and the requirement for a valid connection context.
Ingestion points: --intent and "DESCRIPTION" arguments in CLI commands.
Boundary markers: None explicitly defined in the CLI examples.
Capability inventory: The skill can list and execute actions via membrane action run.
Sanitization: Handled server-side by the Membrane platform.

nets-group