CyberRota Analysis
AI-GeneratedMaxKB versions prior to 2.10.5-lts are vulnerable due to the SandboxShellBackend, which allows untrusted content to execute arbitrary shell commands without human approval. This critical vulnerability can lead to unauthorized command execution, particularly in environments where MAXKB_SANDBOX is disabled, posing significant risks to application security. Organizations using MaxKB should prioritize upgrading to the latest version to mitigate this severe threat.
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
MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupt_on, so human approval is not required. Untrusted chat or ingested content can therefore cause command execution; source deployments with MAXKB_SANDBOX disabled run commands directly as the application user, while the official root container's string-based gosu wrapper allowed shell metacharacters to execute outside the intended sandbox. This issue is fixed in version 2.10.5-lts.