The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is a standard requirement for the Membrane platform and originates from the vendor's ecosystem.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to manage authentications, connections, and actions. These commands are local shell executions intended for the agent to interact with the platform.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from a Nextcloud instance (such as file contents or group names) which could potentially contain untrusted content.
Ingestion points: Data retrieved via membrane action run and membrane request.
Boundary markers: None explicitly defined in the skill instructions.
Capability inventory: The skill has the capability to write to the file system and perform network requests through the Membrane proxy.
Sanitization: Not specified; the skill relies on the agent's internal processing logic for external data.

nextcloud