The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the membrane CLI to perform operations such as membrane login, membrane connect, and membrane action run. These commands are used to manage the authentication lifecycle and execute functional calls to the Conjur API.
[EXTERNAL_DOWNLOADS]: The instructions guide the user to install the @membranehq/cli package from the npm registry. This is a vendor-provided tool required for the skill to communicate with the Conjur environment through the Membrane platform.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it retrieves and processes data from external Conjur endpoints (e.g., secrets, policy metadata). This is a standard risk for integration skills. The instructions do not define specific boundary markers or sanitization logic for the ingested data, which is processed using the CLI's output capabilities.

conjur