The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Membrane CLI (membrane) to perform operations such as listing connections and running actions. This is the standard and intended method for interacting with the Membrane service.
[EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the @membranehq/cli package globally via npm. This is the official command-line interface provided by the vendor (membrane) to manage integrations.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by not hardcoding any API keys or secrets. It utilizes membrane login for user authentication and membrane connect to establish secure connections to LeadBoxer, with credentials managed server-side by the Membrane platform.
[PROMPT_INJECTION]: The skill processes data from LeadBoxer (such as lead details, events, and sessions), which presents a potential surface for indirect prompt injection if external data contains malicious instructions.
Ingestion points: Lead data returned from membrane action run (SKILL.md).
Boundary markers: Not explicitly defined in the provided instructions.
Capability inventory: Capability to create, list, and run actions via the membrane CLI (SKILL.md).
Sanitization: Relies on the agent's underlying safety filters and the vendor's platform sanitization.

leadboxer