The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the installation of the @membranehq/cli package from NPM. This is the official utility provided by the skill author (membranedev) to manage integrations.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform functional operations such as authentication (membrane login), establishing service connections (membrane connect), and executing ticket management tasks (membrane action run). These are standard operations for a platform-based integration.
[PROMPT_INJECTION]: As an integration that processes external ticketing data, the skill possesses an indirect prompt injection surface.
Ingestion points: Data retrieved from Mojo Helpdesk (tickets, comments) via the membrane action run command.
Boundary markers: None explicitly defined in the provided instruction snippets.
Capability inventory: The skill can execute actions and manage connection states using the CLI.
Sanitization: Not explicitly documented; the skill relies on the agent platform's internal safety guardrails.
[SAFE]: The instructions follow security best practices by explicitly directing agents never to request or store user API keys, using server-side connection management instead.

mojo-helpdesk