What is the CVSS score of CVE-2026-23523?

CVE-2026-23523 has a CVSS 3.1 base score of 9.6 (Critical). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H. EPSS exploitation probability: 0.0%.

Which versions of AI / ML are affected by CVE-2026-23523?

Organizations using Dive face critical risk from CVE-2026-23523, a code injection vulnerability rated CVSS 9.6.. A patch is available.

Is there a public PoC exploit available for CVE-2026-23523?

Yes, a public proof-of-concept exploit is available for CVE-2026-23523. Prioritise patching immediately. EPSS: 0.0%.

How to fix or mitigate CVE-2026-23523?

Within 24 hours: Identify all affected systems and apply vendor patches immediately. Validate that input sanitization is in place for all user-controlled parameters.

AI / ML CVE-2026-23523

CRITICAL

Code Injection (CWE-94)

2026-01-16 security-advisories@github.com

RCE Code Injection AI / ML Dive

9.6

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

9.6 CRITICAL

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

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

Required

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 12, 2026 - 21:54 vuln.today

PoC Detected

Feb 09, 2026 - 20:45 vuln.today

Public exploit code

Patch released

Feb 09, 2026 - 20:45 nvd

Patch available

CVE Published

Jan 16, 2026 - 17:15 nvd

CRITICAL 9.6

DescriptionGitHub Advisory

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. Prior to 0.13.0, crafted deeplink can install an attacker-controlled MCP server configuration without sufficient user confirmation and can lead to arbitrary local command execution on the victim’s machine. This vulnerability is fixed in 0.13.0.

AnalysisAI

Dive, an MCP Host Desktop Application for LLM integration, allows code injection prior to version 0.13.0 through malicious tool responses, enabling attackers to execute arbitrary code on the user's machine.

Technical ContextAI

Dive (< 0.13.0) fails to sanitize responses from MCP (Model Context Protocol) tools before processing them (CWE-94). A malicious MCP server can craft tool responses containing injected code that executes in the Dive desktop application context.