The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the npm registry. This is a legitimate tool provided by the vendor for interacting with their platform.
[COMMAND_EXECUTION]: Uses the membrane CLI to manage connections and execute actions. These operations are within the expected scope of a SaaS integration skill.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it retrieves and processes data from external Griffin actions which could contain untrusted content.
Ingestion points: Data returned from membrane action list, membrane action get, and membrane action run (SKILL.md).
Boundary markers: None present; the skill does not specify delimiters or instructions to ignore instructions embedded in the external data.
Capability inventory: The skill can execute existing actions and create new actions based on natural language descriptions via the CLI.
Sanitization: No explicit sanitization or validation of the external data is described.

griffin