HIGHVulnerability
Verified
Global

NVD HIGH: CVE-2026-34163 — FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's M...

Tuesday, March 31, 2026 at 03:16 PM UTC·Source: NIST NVD

Updated: Monday, April 6, 2026 at 12:17 AM UTC

Executive Summary

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInte

Analysis

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5. CVSS Score: 7.7. Published: 2026-03-31T15:16:17.170.

Indicators of Compromise (2)

CVE (1)
CVE-2026-34163
NVDMITRE CVE
Source Attribution

Originally published by NIST NVD on Mar 31, 2026. Verified by: NIST.

Related Threats

MEDIUMVulnerability

The End of Static Security: Why AI Demands Real-Time Microsegmentation

AI is compressing cyberattack timelines from months to minutes. While segmentation has been a gold standard security practice for years, many organizations are still operating with outdated, static approaches.

Bank Info Security
MEDIUMVulnerability

Why Data Security Standards in Cancer Innovation Matter

Cancer research and treatment innovation - and the tech that powers that - requires a great deal of collaboration and data sharing among multiple parties. But keeping that sensitive information secure and private is crucial - and requires adherence to standards, said Baxter Lee of Clearwater.

Bank Info Security
MEDIUMVulnerability

One-Time Passcodes Are Gateway for Financial Fraud Attacks

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/one-time-passcodes-are-gateway-for-financial-fraud-attacks-image_small-6-a-31341.jpg" align=right hspace=4><b>Report Reveals Growing Trend of Fraudsters Intercepting SMS-Based Verification</b><br>Financial institutions have historically relied on one-time passcodes as a primary authentication control for their accountholders. But

Bank Info Security