Ontask

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

This skill is coherent: it expects you to install and use the official Membrane CLI to connect to OnTask and relies on Membrane to manage authentication. Before installing or running commands: 1) verify the npm package name (@membranehq/cli) and the project repository (https://github.com/membranedev/application-skills) on npm/GitHub to ensure you get the legitimate package; 2) be aware that authenticating grants Membrane access to your OnTask data — review the permissions/scopes and the Membrane privacy/terms; 3) because the manifest omitted the required CLI binary, treat the SKILL.md instructions as authoritative and run installs in a controlled environment (or sandbox) if you have concerns; 4) when asked to open an auth URL, check the domain is the expected Membrane URL (avoid responding to unexpected URLs or codes). If you need higher assurance, request an explicit 'requires.binaries' line in the skill metadata and a verified package/source before installing.

Type: OpenClaw Skill Name: ontask Version: 1.0.1 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`) and the execution of shell commands for authentication and remote workflow management. While these actions are aligned with the stated purpose of integrating with the OnTask platform via Membrane, the requirement for global software installation and broad shell/network access qualifies as a high-risk capability under the review criteria. These instructions are primarily located in SKILL.md.