CVE-2026-77521

MaxKB: Prompt-injectable agent can lead to command execution

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

1Panel-dev · MaxKB

CVSS v3.1 GITHUB

10.0 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

EPSS

1.05% chance of exploitation in the next 30 days, 64th percentile

Published

2026-09-21

Updated

2026-09-22

Proof-of-concept exploits (1)

• InertFluid/cve-2026-77521-lab

References

• CVE Record
• NVD entry

Related

• CVE-2026-61732
• CVE-2026-93355