China Academy of Information and Communications Technology Jointly Discovers and Fixes OpenClaw Critical Command Injection Vulnerability

Mars Finance reports that according to market sources, a joint team from China Academy of Information and Communications Technology, Shanghai Jiao Tong University, and Nanjing University conducted a security audit of the open-source autonomous agent framework OpenClaw. They discovered a high-risk command injection vulnerability in its bash-tools module driven by LLMs. The vulnerability stems from the system not properly escaping command-line arguments generated by the LLM. Attackers can bypass regex defenses using诱导性 prompts, enabling remote code execution on the host machine and theft of sensitive data. The research team has completed attack verification across various mainstream model environments, initiated a responsible vulnerability disclosure process, and submitted repair suggestions to the NVDB AI Product Security Vulnerability Database (CAIVD) and the GitHub community.