Verimi

Verimi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Verimi data.

This skill appears to be what it says: a Membrane-based wrapper for Verimi. Before installing or running: 1) verify the @membranehq/cli npm package and its repository (check publisher, GitHub repo, release tags) to avoid a malicious package; 2) prefer using npx for one-off runs if you don't want a global install; 3) during 'membrane login' follow the OAuth browser flow yourself — do not paste credentials or tokens from unknown sources; 4) confirm that the Membrane account you connect with is trusted and that any created actions have the expected scopes; and 5) if you want tighter assurance, review Membrane's privacy/security docs and the Verimi connector implementation in the referenced repository before granting access.

Type: OpenClaw Skill Name: verimi Version: 1.0.3 The skill instructs the agent to perform high-risk operations, including installing a global npm package (`@membranehq/cli`) and executing shell commands to interact with the Membrane platform. It specifically directs the agent to use `membrane action create` to dynamically generate and run actions from a remote service (getmembrane.com), which introduces a significant attack surface for remote code execution or unauthorized data access. While these instructions appear aligned with the stated purpose of Verimi integration, the requirement for global environment modification and the execution of remotely-defined logic are inherently risky behaviors.