Security audit
Security checks across malware telemetry and agentic risk
This appears to be a real UI automation skill, but it needs review because it gives broad browser, desktop, cookie, file, and process-control power without enough safety boundaries.
Install only in an isolated test environment or dedicated profile, not on a personal or production desktop. Avoid real accounts, secrets, sensitive screens, and broad file paths unless you explicitly intend the agent to control them. Treat the shell, cookie/session persistence, file upload, screenshot, and process-kill features as high-risk operations that need user approval and tight scoping.
print(f"[vbox] ⚠️ Xvfb not responding — restarting on {display}...")
# Kill any existing Xvfb
subprocess.run(
["pkill", "-9", "-f", f"Xvfb {display}"],
capture_output=True
)pass
# Kill any remaining
subprocess.run(
["pkill", "-9", "-f", f"remote-debugging-port={CDP_PORT}"],
capture_output=True
)raise RuntimeError("Xvfb failed to start")
# Kill any existing Chrome
subprocess.run(
["pkill", "-9", "-f", f"remote-debugging-port={CDP_PORT}"],
capture_output=True
)print("[vbox] launching Chrome...")
_proc = subprocess.Popen(
["google-chrome"] + CHROME_FLAGS + ["about:blank"],
env=env,
stdout=subprocess.DEVNULL,cmd = [binary] + list(args)
print(f"[launch] {app} on {display}")
proc = subprocess.Popen(
cmd, env=env,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULLdef kill_app(name):
"""Kill app by process name."""
subprocess.run(["pkill", "-f", name], capture_output=True)
time.sleep(0.5)
print(f"[kill] {name}")if running:
print("✅ FM.1 PASSED")
subprocess.run(["pkill", "-x", "nautilus"], capture_output=True)
else:
print(f"❌ FM.1 FAILED - nautilus not running")print(f"[vbox] ⚠️ Xvfb not responding — restarting on {display}...")
# Kill any existing Xvfb
subprocess.run(
["pkill", "-9", "-f", f"Xvfb {display}"],
capture_output=True
)print("[vbox] launching Chrome...")
_proc = subprocess.Popen(
["google-chrome"] + CHROME_FLAGS + ["about:blank"],
env=env,
stdout=subprocess.DEVNULL,65/65 vendors flagged this skill as clean.