The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package via npm. This is the official command-line tool for the Membrane platform, which the skill uses as its runtime environment.
[COMMAND_EXECUTION]: The skill uses various membrane CLI commands to manage the integration lifecycle, including membrane login for authentication, membrane connect for linking HotspotSystem accounts, and membrane action run for executing API requests. These commands are standard for the vendor's ecosystem.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it retrieves and processes data from the HotspotSystem API (such as customer details or transaction logs).
Ingestion points: Data returned from membrane action run is processed by the agent.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: The skill can execute CLI commands, perform network operations via the Membrane platform, and access the local terminal.
Sanitization: There are no explicit instructions for the agent to sanitize or escape the content retrieved from the external API.

hotspotsystem