The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane command-line interface to manage authentication, list connections, and execute HR-related actions.
[EXTERNAL_DOWNLOADS]: It instructs the user to install the @membranehq/cli package via npm. This is a legitimate tool provided by the skill's author (membranedev) for interacting with their service.
[PROMPT_INJECTION]: The skill processes user-supplied natural language through the membrane action list --intent and membrane action create commands. This constitutes an indirect prompt injection surface as it passes untrusted data to a tool, but it is a fundamental part of the intended functionality and includes instructions for handling result schemas.

humi