Code Execution via Malicious MCP in gpt-researcher

Publication date: 2026-08-27

Last updated on: 2026-08-27

Assigner: MITRE

Description

A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-08-27

Last Modified

2026-08-27

Generated

2026-08-28

AI Q&A

2026-08-28

EPSS Evaluated

N/A

NVD

CVE-2026-37006

Affected Vendors & Products

Vendor	Product	Version / Range
gpt-researcher	gpt-researcher	to 0.14.8 (exc)

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-UNKNOWN

Attack-Flow Graph

Executive Summary

This vulnerability is in the WebSocket endpoint of gpt-researcher v0.14.7 and earlier versions. It allows an unauthenticated remote attacker to execute arbitrary code by exploiting malicious Model Context Protocol configurations.

Impact Analysis

An attacker could exploit this to run malicious code on your system without needing authentication. This could lead to unauthorized access, data theft, or further compromise of your environment.

Mitigation Strategies

Immediately upgrade gpt-researcher to a version beyond v0.14.7 to address the WebSocket endpoint vulnerability. Disable unauthenticated access to WebSocket endpoints if possible and review Model Context Protocol configurations for malicious entries.

Hi! I’m here to help you understand CVE-2026-37006. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70