NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering.
Metrics
Affected Vendors & Products
No data.
No data.
No data.
No data.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
| Link | Providers |
|---|---|
| https://nvidia.custhelp.com/app/answers/detail/a_id/5691 |
|
History
Wed, 17 Sep 2025 22:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering. | |
| Weaknesses | CWE-78 | |
| References |
| |
| Metrics |
cvssV3_1
|
MITRE
Status: PUBLISHED
Assigner: nvidia
Published:
Updated: 2025-09-17T21:58:15.643Z
Reserved: 2025-01-14T01:06:28.098Z
Link: CVE-2025-23316
Vulnrichment
No data.
NVD
Status : Received
Published: 2025-09-17T22:15:37.260
Modified: 2025-09-17T22:15:37.260
Link: CVE-2025-23316
Redhat
No data.
OpenCVE Enrichment
No data.