by Kastro
Paper/Archive/CVE-2026-77521

CVE-2026-77521

1Panel-dev MaxKB — MaxKB: Prompt-injectable agent can lead to command execution

EPSS 1%public exploitCVSS 10.0
critical.is priorityof 100
53
CVSS 10.0 (CNA)10.0 / 10 × 3030.0Not in CISA KEV+300.0EPSS percentile 64.3.643 × 2012.9Exploit: SSVC poc+1010.0SSVC exploitation: poc+100.0
Description · from the CVE record

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

ProductAffectedFixed inSource
MaxKB< 2.10.5-lts–CNA

Scores by source

GitHub_M (CNA)10.0CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
CISA ADPSSVCExploitation: poc · Automatable: yes · Technical impact: total

References

exploitgithub.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rxrefgithub.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30earefgithub.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts