Skip to content
NvidiaCVE-2026-47487

Nvidia Triton Inference Server: denial of service

Medium4.4CVE-2026-47487 · Published Aug 4, 2026 · updated Aug 17, 2026

NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might lead to denial of service and information disclosure.

Nvidia advisory

Affected versions

PackageAffectedFixed in
Triton Inference Server
Product
<= 0.0 - 26.02No fix yet
Details and references
CVSS 3.1
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
Severity from
the vendor (its own CVE record or advisory)
Weakness
CWE-22

More Nvidia advisories

All Nvidia
Advisory
Nvidia Dynamo: server-side request forgery
High7.5Aug 4
Nvidia Dynamo: server-side request forgery
High7.5Aug 4
Nvidia Dynamo: server-side request forgery
High7.5Aug 4
Nvidia Dynamo: code execution
Medium6.6Aug 4
Nvidia Dynamo: race condition
Medium6.5Aug 4
Nvidia Dynamo: race condition
Medium6.5Aug 4

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.