Skip to main content

godot-mcp EUVDEUVD-2026-53934

| CVE-2026-19044 LOW
Command Injection (CWE-77)
2026-08-06 VulDB GHSA-rjcp-8q3w-gjhq
1.9
CVSS 4.0 · Vendor: VulDB

Severity by source

Vendor (VulDB) PRIMARY
1.9 MEDIUM
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vuln.today AI
5.3 MEDIUM

Local-only vector with low-privilege MCP access required; unchanged scope and limited C/I/A impact matching CVSS 4.0 base metrics.

3.1 AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
4.0 AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

Primary rating from Vendor (VulDB).

CVSS VectorVendor: VulDB

Attack Vector
Local
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
X

Lifecycle Timeline

3
Analysis Generated
Aug 06, 2026 - 15:58 vuln.today
Severity Changed
Aug 06, 2026 - 15:22 NVD
MEDIUM LOW
CVSS changed
Aug 06, 2026 - 15:22 NVD
4.8 (MEDIUM) 1.9 (LOW)

DescriptionCVE.org

A flaw has been found in LeeSinLiang godot-mcp 0.1.0. Affected by this vulnerability is the function executeOperation of the file src/index.ts of the component create_scene/add_node. This manipulation of the argument projectPath causes command injection. The attack needs to be launched locally. The project was informed of the problem early through an issue report but has not responded yet.

AnalysisAI

Command injection in LeeSinLiang's godot-mcp 0.1.0 allows local low-privileged users to execute arbitrary OS commands by supplying a crafted projectPath argument to the executeOperation function in src/index.ts, specifically through the create_scene and add_node MCP operation handlers. This Model Context Protocol server for the Godot game engine was disclosed via a GitHub issue report that the project maintainer has not yet addressed. No active exploitation has been confirmed and no CISA KEV listing exists, though the CVSS 4.0 temporal metric E:P confirms publicly available proof-of-concept exploit code.

Technical ContextAI

godot-mcp is a Model Context Protocol (MCP) server that bridges AI assistant clients (such as Claude or similar LLM-based tools) with the Godot game engine, enabling AI-driven scene creation, node manipulation, and other editor operations. The root cause is CWE-77 (Improper Neutralization of Special Elements used in a Command): the executeOperation function in src/index.ts accepts a projectPath argument from MCP operation calls and passes it unsanitized to an underlying shell command, allowing injection of arbitrary shell metacharacters. The affected CPE is cpe:2.3:a:leesinliang:godot-mcp:*:*:*:*:*:*:*:*, with version 0.1.0 confirmed by EUVD-2026-53934. The wildcard CPE notation suggests the flaw may not be version-scoped.

RemediationAI

No vendor-released patch has been identified at time of analysis - the project maintainer has not responded to the GitHub disclosure at https://github.com/LeeSinLiang/godot-mcp/issues/1. Developers should discontinue use of godot-mcp 0.1.0 in shared or multi-user environments until a fix is released. As a compensating control, restrict MCP server access to fully trusted local users only, preventing untrusted principals from invoking create_scene or add_node operations with attacker-controlled projectPath values. Sanitize or reject projectPath inputs containing shell metacharacters (semicolons, pipes, backticks, dollar signs, ampersands) at the application boundary. Monitor the repository at https://github.com/LeeSinLiang/godot-mcp for patch releases. Note that input validation alone is insufficient without a code-level fix; developers comfortable modifying the codebase should replace shell interpolation with a safe command execution API that passes arguments as discrete array elements rather than a composed shell string.

Share

EUVD-2026-53934 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy