Windows UI Automation

Automate Windows GUI interactions (mouse, keyboard, windows) using PowerShell. Use when the user needs to simulate user input on the desktop, such as moving the cursor, clicking buttons, typing text in non-web apps, or managing window states.

Install only if you intentionally want an agent to operate your live Windows desktop. Keep sensitive apps closed or unfocused, verify the target window with screenshots or active-window checks, and require explicit confirmation before clicks or keystrokes that could submit, delete, purchase, send, approve prompts, or change settings.

Type: OpenClaw Skill Name: windows-ui-automation Version: 1.0.0 The skill bundle provides powerful Windows UI automation capabilities, including simulating arbitrary mouse movements, clicks, and keyboard input, as well as managing window states. While these actions align with the stated purpose of 'Windows UI Automation', they represent inherently high-risk behaviors. The `keyboard_control.ps1.txt` and `mouse_control.ps1.txt` scripts use `System.Windows.Forms.SendKeys` and direct `user32.dll` calls via `Add-Type` to achieve full control over the desktop UI. The `SKILL.md` also demonstrates the use of `WScript.Shell` for window activation. There is no evidence of intentional malicious activity like data exfiltration or persistence, but the extensive control over the user's desktop makes this skill highly susceptible to abuse if the agent is compromised or given ambiguous instructions, classifying it as suspicious due to its significant potential for harm.