Security checks across malware telemetry and agentic risk
This is a legitimate-looking monitoring platform, but it needs Review because it can run other skills unsandboxed, persist scheduled uploads, transmit telemetry, and overstates some credential-storage protections.
Install only if you are comfortable with a broad monitoring tool that can execute installed skills, store an agent API key, run local/server dashboards, and upload reports. Prefer using it in a sandbox or dedicated environment, avoid enabling scheduled uploads until you verify the destination and payloads, do not rely on the fallback credential store as strong encryption, and review the bundled server authentication before exposing it beyond localhost.
cmd.append(str(v))
try:
result = subprocess.run(
cmd,
capture_output=True,
text=True,"""直接运行并传入 symbol"""
entry_path = os.path.join(self.info.dir_path, self.info.entry_file)
try:
result = subprocess.run(
[sys.executable, entry_path, symbol],
capture_output=True,
text=True,# 查找目标函数
func = None
if task_name and hasattr(module, task_name):
func = getattr(module, task_name)
elif hasattr(module, "main"):
func = module.main
elif hasattr(module, "run"):cmd = f"python3 {PROJECT_ROOT / 'skills_monitor_web.py'} --port {port} {demo_flag} {debug_flag}"
print(f"🚀 启动 Web 面板: http://127.0.0.1:{port}")
os.system(cmd.strip())
def cmd_upload(args):64/64 vendors flagged this skill as clean.