PC Control

Remote Windows desktop control from WSL/Linux via screenshot + mouse/keyboard simulation. Use when: user asks to control their PC, click something, open an a...

This skill implements a powerful capability (remote control of your Windows desktop). The code matches the description, but the package metadata understates what it needs: you will need a Windows Python, PowerShell, and WSL utilities (wslpath). Before installing, verify you trust the skill source and inspect the files. Specific recommendations: 1) Confirm config.json points to the correct Windows python and PowerShell paths; prefer installing dependencies into a dedicated virtualenv rather than the system Python. 2) Limit network exposure: the server binds to 127.0.0.1, but ensure no port forwarding or reverse tunnels expose it externally. 3) Protect the skill directory: .auth_token is stored in plaintext — restrict filesystem permissions and remove the token file when not needed. 4) Consider requiring stronger auth or rotating the token between sessions. 5) Review the launcher stop code (it may forcibly stop python processes matching server.py) to avoid killing unrelated processes. 6) If you are uncomfortable with full GUI control, test in an isolated VM or disposable account first. If you want me to, I can point out the exact lines to change to require authentication on /status, to write token with restricted permissions, or to make the launcher use a venv.

Type: OpenClaw Skill Name: pc-control Version: 1.0.0 The skill provides remote Windows desktop control via screenshot, mouse, and keyboard simulation, which is an inherently high-risk capability. While the implementation includes security measures like localhost binding and ephemeral token authentication for its FastAPI server (scripts/server.py), and the SKILL.md does not contain prompt injection attempts, the use of PowerShell via `subprocess.run` in `scripts/install.py` and `scripts/launcher.py` to install dependencies and manage the server process represents powerful system command execution. These capabilities, though necessary for the skill's stated purpose, are significant and warrant a 'suspicious' classification due to their potential for misuse if the agent or skill configuration were compromised, even without clear evidence of intentional malicious behavior within the skill itself.