NVIDIA Triton Inference Server: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause a…

Who is affected

NVIDIA Triton Inference Server is software that runs AI models so that other apps and services can send it requests and get answers back. This flaw affects NVIDIA Triton Inference Server for Linux. No specific affected versions are named for this flaw. An attacker could trigger a memory handling mistake in the server. This might cause a denial of service, meaning the server could crash or stop answering requests, so the tools that rely on it could stop working. This flaw is rated High. It only matters if your organization runs this server on Linux, either yourself or through a provider.

What to do

1. Find out whether your organization runs NVIDIA Triton Inference Server on Linux, and who installed it or looks after it (a staff member, a volunteer, or an IT provider).
2. If someone in your organization runs it, ask them to update it. No fixed version is named for this flaw yet, so they should check the vendor advisory linked on this page for a fixed release and install it.
3. If an IT provider or vendor runs it for your organization, send them this advisory and ask when the update will be done.

Analysis written from the source record as of October 25, 2026 and reviewed before publishing.