Cyber Posture

CVE-2026-44450

Critical
Microsoft: not affectedMSmacOS: not affectedMacLinux: not affectedLnxMobile: not affectedMobNetwork: not affectedNetApplication: not affectedAppOther: affectedOth

Published: 26 May 2026

Published
26 May 2026
Modified
27 May 2026
KEV Added
—
Patch
—
CVSS Score 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
EPSS Score 0.0007 21.7th percentile
Risk Priority 20 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2026-44450 is a critical-severity Argument Injection (CWE-88) vulnerability. Its CVSS base score is 9.9 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 21.7th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.

Threat & Defense at a Glance

What attackers do: exploitation maps to Exploit Public-Facing Application (T1190) and 1 other technique.
Threat & Defense Details

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
attack.mitre.org →
Why these techniques?

CWE-88 argument injection in public-facing MCP endpoint allows any authenticated user to pass code-execution flags (-e/-c) to allowlisted interpreters, directly enabling remote code execution via T1190 and T1059.

Confidence: HIGH · MITRE ATT&CK Enterprise v18.1

NVD Description

Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on…

more

the allowlist accepts an inline-code execution flag (-e for node/bun, -c for python3/deno), giving any logged-in user arbitrary OS-level code execution on the Lumiverse server. The route requires only requireAuth (not requireOwner). The server binds on all interfaces (::) and the host-header rebinding check is bypassed trivially by any HTTP client that sends Host: localhost:<port> directly, making this exploitable from any machine with network access to the server port. This vulnerability is fixed in 0.9.7.

Deeper analysisAI

Automated synthesis unavailable for this CVE.

Details

CWE(s)
CWE-88
OWASP Top 10 Web 2025
A05:2025

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ai, mcp

EU & UK References

Regulatory context (EU CRA / NIS2 / DORA / UK NIS Regulations)

EU Cyber Resilience Act — coordinated disclosure

Critical and high-severity vulnerabilities in products with digital elements may trigger coordinated-disclosure obligations under the EU Cyber Resilience Act (CRA, Regulation 2024/2847). Manufacturers placing products on the EU market must notify ENISA and the relevant CSIRTs without undue delay once active exploitation is known.

References