当用户想要**Windows自动化**、**自动打开CMD**、**在指定目录执行命令**、**运行bat脚本**、**GitHub自动下载最新版**、**一键下载仓库源码**、**桌面GUI自动化**、**pyautogui任务**、**全屏可视化提示**、**鼠标单击强制停止**、**输入法自动切换**、**...

This skill appears to implement the claimed Windows automation features, but it performs intrusive environment actions without explicit user consent: on import it runs a fix_setuptools pip install, it auto-installs packages, and its env_manager can create a shared venv and re-launch the program inside it. Before installing or running: - Only run on Windows and preferably in an isolated environment (VM/container) or throwaway account. - Inspect and remove/disable ensure_package.fix_setuptools() automatic call (it runs pip on import). Consider making package installation explicit instead of automatic. - Be aware running operations.py will create a venv path (VENV_DIR), logs, and model/data dirs; confirm those paths are acceptable. - If you only need simple CMD automation or GitHub ZIP downloads, consider extracting and running only the minimal modules (cmd_task/github_download and the overlay) after removing auto-install and env_manager bootstrap code. - If you trust the author and intend to use it, run it interactively the first time so you can observe prompts and network activity; otherwise run in an isolated VM and audit network traffic. I assessed this as 'suspicious' (not clearly malicious) because the unexpected auto-install and environment-modifying behavior could be legitimate design choices but are disproportionate and risky without clear prompt/consent. Additional author provenance (official homepage, repo, maintainer identity) or changing the code to remove import-time installs would increase confidence.

Type: OpenClaw Skill Name: claw-windows-automator Version: 1.0.2 The skill bundle provides powerful Windows desktop automation capabilities, including executing arbitrary commands in CMD (cmd_task.py) and automating browser downloads via keyboard simulation (github_download.py). It uses pyautogui to simulate user input and ctypes to manipulate window styles and input methods, which are high-risk behaviors. While the skill includes safety features like a full-screen visual overlay and a mouse-click emergency stop (gradient_overlay.py), the inherent ability to perform GUI-level automation and arbitrary command execution provides a significant attack surface for prompt injection or agent misuse. No clear evidence of intentional malice, such as data exfiltration or backdoors, was found.