China's Ministry of Industry and Information Technology (MIIT) has warned that the OpenClaw open-source AI assistant could pose security risks under default or improper configurations, exposing users to cyberattacks and data breaches.
OpenClaw, which is created by Austrian developer Peter Steinberger, is designed to allow large language models to operate computers autonomously, controlling files, executing commands and interacting through messaging applications such as WhatsApp and Telegram.
According to the National Vulnerability DataBase (NVDB) of the ministry, users become susceptible to security risks such as data leaks and devices subject to remote control when using OpenClaw in the absence of effective permission controls, auditing mechanisms and security reinforcement.
The AI agent's vulnerability lies in its operation within "blurred trust boundaries" during its deployment, and its features including continuous operation, autonomous decision-making and access to system and external resources.
Experts advise that relevant organizations and individuals disable unnecessary public network access when deploying OpenClaw applications, improve security mechanisms such as identity authentication, access control, data encryption and security auditing, and continuously pay attention to official security announcements and hardening recommendations.
Ministry warns of security risks in OpenClaw AI agent
