The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from npm. This is a scoped package belonging to the skill's authoring organization and is the primary tool for the integration.
[COMMAND_EXECUTION]: The skill uses the membrane command-line utility to authenticate, manage connections, and execute actions. These operations are restricted to the functionality provided by the vendor's platform.
[DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. Authentication is handled server-side by the Membrane platform, and the skill explicitly advises against asking users for API keys.
[PROMPT_INJECTION]: No evidence of prompt injection, role-play overrides, or system prompt extraction was found in the instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes data returned from the Cradlepoint API through the membrane action run command. This represents a potential indirect injection surface where external data enters the agent's context, but this is consistent with the skill's primary purpose of data integration.

cradlepoint