# CVE-2026-37006: gpt-researcher WebSocket code execution via Model Context Protocol

Source: https://junglewise.ai/threats/cve-2026-37006-gpt-researcher-websocket-code-execution-via-model-context  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-27. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-37006 · Severity: critical · CVSS 9.8 · Published 2026-08-27

gpt-researcher is a framework for autonomous AI research agents. A vulnerability in its WebSocket endpoint allows unauthenticated remote attackers to execute arbitrary code by sending malicious Model Context Protocol configurations, potentially compromising servers running affected versions and enabling full system control.

## Quick answers

**Is CVE-2026-37006 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-37006 being exploited in the wild.

**How severe is CVE-2026-37006?** Critical severity, with a CVSS score of 9.8, published 27 August 2026.

**Which products and versions are affected?** gpt-researcher gpt-researcher v0.14.7 and before.

**Is there a fix for CVE-2026-37006?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-37006 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-37006?** Check whether anything you run is named in the advisory. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability is a remote code execution flaw in the WebSocket endpoint of gpt-researcher v0.14.7 and earlier. An unauthenticated attacker can send specially crafted Model Context Protocol (MCP) configurations over the WebSocket connection to trigger code execution on the server. The WebSocket endpoint lacks proper input validation and authentication controls, allowing the attack to be conducted without credentials from a network-accessible position. Successful exploitation grants the attacker arbitrary code execution in the context of the application.

## Affected products

- gpt-researcher gpt-researcher v0.14.7 and before

## Timeline

- 2026-08-27: disclosed

## References

- [http://gpt-researcher.com/](http://gpt-researcher.com/)
- [https://yerangamage.com/cves/detail/?slug=gptresearcher-websocket-rce](https://yerangamage.com/cves/detail/?slug=gptresearcher-websocket-rce)