The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @membranehq/cli package from the official NPM registry to facilitate interaction with the Membrane platform. This is a standard dependency for the vendor's integration tooling.
[COMMAND_EXECUTION]: The integration relies on the membrane CLI for all operations, including session authentication (membrane login), establishing service connections (membrane connect), and executing specific project management tasks (membrane action run).
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection (Category 8) because it processes data from an external source (FTrack).
Ingestion points: Data enters the context from FTrack entities like notes, task descriptions, and project metadata via membrane action run outputs.
Boundary markers: No specific delimiters or "ignore instructions" markers are defined in the instructions for the retrieved data.
Capability inventory: The agent has the ability to execute potentially destructive actions such as delete-project and update-task, as well as dynamically generating new logic through membrane action create.
Sanitization: The skill does not specify any sanitization or validation of the content retrieved from FTrack before it is interpreted by the agent.

ftrack