The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via npm. This is the official CLI tool for the Membrane platform, which is the infrastructure used by this skill.
[COMMAND_EXECUTION]: The skill utilizes several CLI commands (e.g., membrane login, membrane connect, membrane action run) to manage authentication and interact with Employment Hero data. These commands are standard operations for the Membrane ecosystem.
[PROMPT_INJECTION]: The skill processes data from an external HR platform (Employment Hero). This represents a surface for indirect prompt injection if the retrieved employee records or documents contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested via membrane action run when retrieving employee details, documents, or leave requests.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: The skill can perform write actions (e.g., update-personal-details, quick-add-employee) and execute platform-specific commands.
Sanitization: Not specified; the skill relies on the underlying agent's standard data handling.

employment-hero