MaxKB: Prompt-injectable agent can lead to command execution
1Panel-dev MaxKB
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| 1Panel-dev MaxKB |
| No fix yet |
Original 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.
From the CVE record · GitHub_M