The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the installation of the @membranehq/cli package from the public NPM registry. This is an official tool provided by the vendor for managing the integration.\n- [COMMAND_EXECUTION]: The skill relies on shell command execution via the membrane CLI to perform authentication, connection setup, and data operations against Mindbreeze.\n- [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes external data from Mindbreeze searches and records.\n
Ingestion points: Untrusted external data from Mindbreeze is retrieved via membrane action run and ingested into the agent context.\n
Boundary markers: No specific boundary markers or 'ignore' instructions are provided to delimit the retrieved data.\n
Capability inventory: The skill possesses the capability to execute shell commands through the Membrane CLI.\n
Sanitization: The instructions do not specify any sanitization, validation, or escaping of the external content retrieved.

mindbreeze