CVE-2026-77521

MaxKB: Prompt-injectable agent can lead to command execution

Published 21 Sep 2026 • Updated 21 Sep 2026

Severity: CRITICAL

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 (1)

• 1Panel-dev MaxKB

Problem types

• CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
• CWE-250: Execution with Unnecessary Privileges
• CWE-749: Exposed Dangerous Method or Function

References (3)

• https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx
• https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea
• https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts