Upserve

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

This skill is coherent: it uses the Membrane CLI to manage Upserve connections and actions and does not ask for unrelated credentials. Before installing or running it, verify you trust the @membranehq npm package (check the npm org and GitHub source), and be aware that `npm -g` will install a global binary. In sensitive or locked-down environments, prefer installing the CLI locally (without -g) or review the CLI source first. Also ensure you are comfortable granting the Membrane account the permissions needed to access your Upserve data since authentication is handled through Membrane's service.

Type: OpenClaw Skill Name: upserve Version: 1.0.1 The skill instructions in SKILL.md direct the AI agent to perform high-risk operations, including global software installation (npm install -g @membranehq/cli) and the execution of shell commands for authentication and data management. While these actions are aligned with the stated purpose of integrating with the Membrane platform, the pattern of constructing shell commands with JSON input (e.g., 'membrane action run --input ...') introduces a significant risk of shell injection if user-provided data is not properly sanitized by the agent. Additionally, the ability to dynamically create and execute new actions via 'membrane action create' provides a powerful mechanism for arbitrary code execution within the Membrane environment.