The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill involves installing the @membranehq/cli package, which is an official tool provided by the vendor (membranedev) for interacting with their service.
[COMMAND_EXECUTION]: The skill uses standard CLI commands (membrane login, membrane connect, etc.) to facilitate interaction with the Labs64 NetLicensing API through a secure proxy.
[PROMPT_INJECTION]: The skill exposes an interface for processing user-supplied data via API actions, representing a surface for indirect injection.
Ingestion points: Untrusted data enters the agent context through the --input flag in membrane action run.
Boundary markers: None present in the instructions.
Capability inventory: Subprocess execution of the membrane CLI and network operations through the vendor's proxy.
Sanitization: Validation is performed by the external CLI tool and the destination API.

labs64-netlicensing