The Agent Skills Directory

[COMMAND_EXECUTION]: Uses the membrane CLI to manage connections and execute API-driven actions such as listing users, groups, and events.
[EXTERNAL_DOWNLOADS]: Recommends the installation of the @membranehq/cli package from the npm registry, which is the official tool provided by the vendor for this integration.
[PROMPT_INJECTION]: The skill processes data from the Heartbeat API, creating a surface for potential indirect prompt injection if the ingested data contains malicious instructions.
Ingestion points: Data retrieved through membrane action run and membrane request commands (e.g., user profiles, document contents).
Boundary markers: No specific markers or delimiters are defined to isolate API data from the agent's instructions.
Capability inventory: Full access to the membrane CLI tools and the ability to perform further network requests via the proxy.
Sanitization: The skill relies on standard platform behavior and does not implement explicit validation or sanitization for the retrieved API content.

heartbeat