NVIDIA Triton Inference Server: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause…
NVIDIA Triton Inference Server
More for NVIDIA Triton Inference Server RSS feed for NVIDIA Triton Inference Server
- Severity
- Critical, CVSS 9.1
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
- Record
- CVE-2026-47606
- Affects
- NVIDIA Triton Inference Server
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- August 18, 2026
- Source last modified
- October 22, 2026
Description
NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause an absolute path traversal. A successful exploit might lead to code execution and information disclosure.
Description quoted from the NVD record.
Who is affected
NVIDIA Triton Inference Server, software that runs AI models so that other programs and apps can send it requests and get answers, has a flaw in its Linux version. No specific affected versions are named for this flaw, so treat any Linux installation as possibly affected. An attacker could trick the server into reaching files by giving it a full file location outside the places it is meant to use. If this succeeds, the attacker might be able to run their own code on the server and see information they should not have. This flaw is rated Critical.
What to do
- Find out whether your organization uses NVIDIA Triton Inference Server on Linux, and who installed it or runs it: someone on your staff, or an IT provider or vendor who manages it for you.
- No fixed version is named for this flaw yet, so the person who runs the server should check the vendor advisory linked on this page for a fixed release and install it as soon as it is available.
- If an IT provider or vendor runs the server for your organization, send them this advisory and ask when the update will be done.
Analysis written from the source record as of October 22, 2026 and reviewed before publishing.