The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI (@membranehq/cli) globally via NPM. This package is an official tool provided by the vendor for platform interaction and authentication management.\n- [COMMAND_EXECUTION]: The skill utilizes several CLI commands including membrane login, membrane search, membrane connect, and membrane action run to interact with the Linkly API and manage the integration environment.\n- [SAFE]: The skill demonstrates a strong security posture by delegating credential management to the Membrane platform. It explicitly instructs the agent not to request API keys or tokens from users, instead leveraging server-side OAuth flows managed by the CLI.\n- [SAFE]: Indirect Prompt Injection Surface: The skill ingests data from the Linkly API (ingestion points: membrane action run and membrane request outputs mentioned in SKILL.md). While specific boundary markers are not defined, the agent's capabilities are scoped to the vendor-controlled CLI environment (capability inventory: membrane CLI), and the risk is assessed as safe given the primary purpose of the integration.

linkly