CVE-2026-24271

Published: Jul 14, 2026Modified: Jul 15, 2026Deferred

6.2

Vector

CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Exploitability: 2.5 / Impact: 3.6

Source: psirt@nvidia.com (Secondary)

Description

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service.

Related CWEs

CWE-770

Allocation of Resources Without Limits or Throttling

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor.

References (2)

https://nvd.nist.gov/vuln/detail/CVE-2026-24271

Source: psirt@nvidia.com

https://www.cve.org/CVERecord?id=CVE-2026-24271

Source: psirt@nvidia.com

Timeline

No history available yet.