Security checks across malware telemetry and agentic risk
This desktop automation skill is mostly coherent, but it gives an agent broad control over the local desktop and filesystem without clear safety boundaries.
Install only if you intentionally want an agent to control a desktop session. Prefer a disposable VM or low-privilege test account, keep sensitive windows closed, restrict scripts and file paths yourself, and require human review before running automation that types, clicks, opens or closes apps, captures screenshots, or writes files.
def open_application(self, name: str) -> None:
"""Open application"""
if self.platform == 'linux':
subprocess.run(['xdotool', 'search', '--name', name,
'windowactivate', '2>/dev/null'], check=False)
# If not found, try to launch
app_map = {def close_application(self, name: str) -> None:
"""Close application"""
if self.platform == 'linux':
subprocess.run(['xdotool', 'search', '--name', name,
'windowkill'], check=False)
def read_file(self, path: str) -> Optional[bytes]:'chrome': 'google-chrome'
}
if name in app_map:
subprocess.Popen([app_map[name]])
def close_application(self, name: str) -> None:
"""Close application"""def analyze_desktop():
# 截图
result = subprocess.run(
["python3", "skills/desktop-control/scripts/main.py",
"screenshot", "--base64"],
capture_output=True, text=TrueVirusTotal findings are pending for this skill version.