Security audit
Security checks across malware telemetry and agentic risk
This is a real Linux desktop-control skill, but its standalone runtime auto-grants powerful screen, input, app, and clipboard permissions without an actual user approval step.
Install only if you intentionally want an agent to control a trusted Linux desktop session. Treat it as high-privilege: it can see unredacted screen contents, use mouse and keyboard input, read or write clipboard data when requested, launch already-granted apps, and install Python packages on first run. Review or change the auto-approval behavior before using it around sensitive apps or private data.
lastScreenshotDims?: ScreenshotDims
}
function autoApprovePermission(req: CuPermissionRequest): CuPermissionResponse {
const granted = req.apps
.filter(app => app.resolved && !app.alreadyGranted)
.map(app => ({getDisplayPinnedByModel: () => state.displayPinnedByModel ?? false,
getDisplayResolvedForApps: () => state.displayResolvedForApps,
getLastScreenshotDims: () => state.lastScreenshotDims,
onPermissionRequest: async req => autoApprovePermission(req),
onAllowedAppsChanged: (apps, flags) => {
state.allowedApps = [...apps]
state.grantFlags = flagsmss>=10.1.0 Pillow>=11.3.0 pyautogui>=0.9.54 psutil>=7.0.0
mss>=10.1.0 Pillow>=11.3.0 pyautogui>=0.9.54 psutil>=7.0.0 python-xlib>=0.33
mss>=10.1.0 Pillow>=11.3.0 pyautogui>=0.9.54 psutil>=7.0.0 python-xlib>=0.33
mss>=10.1.0 Pillow>=11.3.0 pyautogui>=0.9.54 psutil>=7.0.0 python-xlib>=0.33
Pillow>=11.3.0 pyautogui>=0.9.54 psutil>=7.0.0 python-xlib>=0.33
66/66 vendors flagged this skill as clean.
Detected: suspicious.dangerous_exec