Vulnerability · Published Sep 21, 2026 · Assigned by GitHub_M
CVE-2026-77521MaxKB: Prompt-injectable agent can lead to command execution
Critical 10.0
In plain English
A critical-severity OS command injection in MaxKB from 1Panel-dev. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 1.0% (higher than 64% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code.
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| 1Panel-dev | MaxKB | < 2.10.5-lts |
Weakness: CWE-78, CWE-250, CWE-749 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H