Rescuetime

RescueTime integration. Manage Persons, Activities, Categories, Goals, Reports. Use when the user wants to interact with RescueTime data.

This skill is coherent, but take standard precautions before installing the Membrane CLI: 1) Verify the npm package (@membranehq/cli) and its publisher (check npmjs.com, GitHub repo, and package signatures if available). 2) Review Membrane's privacy/security documentation and the RescueTime scopes you’ll grant—Membrane will mediate access to your RescueTime data. 3) Installing global npm packages runs code on your machine—consider installing in a controlled environment or using npx rather than a global install. 4) Expect the CLI to persist tokens locally; if that matters, run it in an isolated account/container. If you accept those tradeoffs, the skill itself is internally consistent and matches its description.

Type: OpenClaw Skill Name: rescuetime-integration Version: 1.0.3 The skill instructs the agent to perform high-risk operations, including the global installation of a third-party CLI tool (`npm install -g @membranehq/cli@latest`) and delegating all authentication and logic to an external service (Membrane). It includes instructions for the agent to 'create' new actions on the fly via natural language descriptions sent to the Membrane platform, which effectively allows remote logic generation and execution. While these features are aligned with the stated purpose of using the Membrane integration platform, the requirement for global software installation and the delegation of control to an external binary/service (getmembrane.com) represent a significant attack surface and potential for unauthorized remote control or data access.