CVE-2026-77521

10 CRITICALpublic exploit available

Published 2026-09-21 · Updated 2026-09-22

AI risk analysis

Summary: The flaw allows untrusted chat or content to execute arbitrary shell commands, posing a significant risk to system security.
Exploitability: Exploitation is relatively easy given untrusted input, requiring only the presence of the affected MCP tool or skill.
Blast radius: If exploited, this could lead to complete system compromise, allowing attackers to execute arbitrary commands as the application user or root.
Detection: No reliable host or network indicator is derivable from the published description.
Prioritized remediation: Upgrade to version 2.10.5-lts or later.

rceshell-execaiopen-source

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD 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.

CVSS vector

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

Weaknesses

CWE-78, CWE-250, CWE-749

Public exploit & PoC references

References

Data: NVD (public domain). Analysis: local $0 model. Defensive use only.