openclaw omni expert

OpenClaw全能专家系统；支持多种远程软件(UU/RustDesk/ToDesk/向日葵/RDP)、一键安装、TOP3专家诊断、全自动驾驶、Agent/Workflow编排、工具链配置、记忆系统、插件开发、监控运维、100+实战案例库和故障排查手册；用户说"安装 OpenClaw"、"配置 OpenClaw"...

This package appears to implement a full remote‑control/autopilot system and will access and persist local configuration (e.g., ~/.openclaw, APPDATA RustDesk config), can read/write passwords and SSH keys (if given), and runs many external CLI commands (ssh, scp, rustdesk, uu, todesk, sunlogin, mstsc, etc.). Before installing or running it: 1) Review the code (especially files like rustdesk_control.py, remote_desktop_control.py, autopilot.py, install_openclaw.sh) to confirm there are no unexpected remote endpoints or hidden uploads; 2) Do not supply real SSH private keys or admin credentials — use throwaway accounts/VMs for testing; 3) Expect the tool to create and modify files under your home directory (learned cases, configs) and possibly append passwords to app config files; 4) If you need to run it, prefer an isolated sandbox or VM and restrict network access until you trust it; 5) Ask the publisher to update the registry metadata to list required binaries and explain precisely what config paths it will read/write and why. These steps will reduce the risk of accidental credential exposure or unintended remote actions.

Type: OpenClaw Skill Name: openclaw-omni-expert Version: 1.0.0 The bundle provides extensive remote administration and UI automation capabilities, including SSH management, remote command execution, and mouse/keyboard control across multiple platforms (UU, RustDesk, ToDesk, RDP, etc.). While these features are aligned with the stated purpose of an 'Omni Expert' system, the high-privilege nature of the scripts (e.g., scripts/remote-helper.py, scripts/autopilot.py, and scripts/remote_automation.py) and the handling of sensitive credentials like API keys and SSH keys pose a significant security risk. No explicit malicious intent or unauthorized data exfiltration was found, but the broad remote execution surface and the ability to simulate user input remotely warrant a suspicious classification.