CyberRota Analysis
AI-GeneratedOpenClaw versions prior to 2026.8.1 are vulnerable due to a sandbox policy bypass in the MCP loopback component, allowing unauthorized access to tools that should be restricted. This vulnerability enables attackers to list and execute denied tools, potentially compromising data integrity and security. Organizations using affected versions should prioritize updating to mitigate the risk of unauthorized actions within sandboxed environments.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions the operator intended to exclude from the sandbox.