CVE-2026-65122: NVIDIA TensorRT out-of-bounds read

CVE-2026-65122 · Severity: medium · CVSS 5.5 · Published 2026-10-06

NVIDIA TensorRT is a neural network inference framework used to optimize and deploy deep learning models in production environments. A vulnerability in TensorRT allows an attacker to trigger an out-of-bounds memory read, which can crash the application and cause a denial of service, disrupting AI inference services.

Technologies: Nvidia TensorRT. Vendors: Nvidia.

Quick answers

Is CVE-2026-65122 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-65122 being exploited in the wild.
How severe is CVE-2026-65122?
Medium severity, with a CVSS score of 5.5, published 6 October 2026.
Which products and versions are affected?
NVIDIA TensorRT.
Is there a fix for CVE-2026-65122?
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-2026-65122 attacked?
It is in a software library.
Am I affected by CVE-2026-65122?
Check whether you run Nvidia TensorRT. 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 contains an out-of-bounds read vulnerability that can be triggered by an attacker to access memory outside allocated bounds. This leads to denial of service through application crash. The advisory does not specify attack vectors, authentication requirements, or whether a fix is available.

Affected products

  • NVIDIA TensorRT

Timeline

  • 2026-10-06: disclosed

References

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