CVE-2026-44284
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
Description
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
INFO
Published Date :
May 8, 2026, 11:16 p.m.
Last Modified :
July 24, 2026, 8:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | MEDIUM | [email protected] |
Solution
- Update FastGPT to version 4.14.17 or later.
- Review MCP tool configurations for suspicious URLs.
- Ensure workflow runners are updated and validated.
Public PoC/Exploit Available at Github
CVE-2026-44284 has a 1 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-44284.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-44284 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-44284
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
The Project shares all information on MCP related CVE's published
mcp mcp-security mcp-cve
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-44284 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-44284 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Translated by [email protected]
Jul. 24, 2026
Action Type Old Value New Value Added Translation Title: FastGPT de labring, Description: FastGPT es una plataforma de creación de agentes de IA. Antes de la versión 4.14.17, FastGPT tenía una brecha de protección SSRF inconsistente en el manejo de URL de herramientas MCP. Los puntos finales directos de vista previa/ejecución de MCP ya rechazaban las URL de red interna/privada, pero los puntos finales de creación/actualización de herramientas MCP aún podían guardar una URL de servidor MCP interna. Esa URL almacenada podría ser utilizada más tarde por la ejecución del flujo de trabajo sin revalidar el destino. Un usuario autenticado con permiso para crear o administrar conjuntos de herramientas MCP podría almacenar un punto final interno como http://localhost:3000/mcp y más tarde hacer que el ejecutor de flujos de trabajo de backend de FastGPT se conectara a ese destino interno. Este problema ha sido parcheado en la versión 4.14.17. -
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'labring', 'product': 'FastGPT', 'versions': [{'status': 'affected', 'version': '< 4.14.17'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-44284', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-05-11T15:57:46.900457Z'} -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
May. 11, 2026
Action Type Old Value New Value Added Reference https://github.com/labring/FastGPT/pull/6826 Added Reference https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq -
New CVE Received by [email protected]
May. 08, 2026
Action Type Old Value New Value Added Description FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L Added CWE CWE-918 Added Reference https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69 Added Reference https://github.com/labring/FastGPT/pull/6826 Added Reference https://github.com/labring/FastGPT/releases/tag/v4.14.17 Added Reference https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq