CVE-2026-24269: NVIDIA TensorRT-LLM server-side request forgery

CVE-2026-24269 · Severity: high · CVSS 7.1 · Published 2026-10-27

NVIDIA TensorRT-LLM is a software library used to optimize and deploy large language models. A server-side request forgery vulnerability in this library could allow an attacker to make unauthorized network requests, leading to unauthorized access to internal systems, information disclosure, and the ability to modify data.

Technologies: Nvidia TensorRT-LLM. Vendors: Nvidia.

Quick answers

Is CVE-2026-24269 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-24269 being exploited in the wild.
How severe is CVE-2026-24269?
High severity, with a CVSS score of 7.1, published 27 October 2026.
Which products and versions are affected?
NVIDIA TensorRT-LLM.
Is there a fix for CVE-2026-24269?
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-2026-24269 attacked?
It is attacked over the network.
Am I affected by CVE-2026-24269?
Check whether you run Nvidia TensorRT-LLM. 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

TensorRT-LLM contains a server-side request forgery (SSRF) vulnerability that allows an attacker to craft requests that cause the server to make unintended outbound network connections. Exploitation could result in information disclosure from internal services and data tampering on accessible backend systems, depending on network configuration and access controls.

Affected products

  • NVIDIA TensorRT-LLM

Timeline

  • 2026-10-27: disclosed

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.