NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.
Subscriptions
Tracking
Sign in to view the affected projects.
Advisories
| Source | ID | Title |
|---|---|---|
EUVD |
EUVD-2023-35373 | NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering. |
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/5509 |
|
History
Tue, 17 Jun 2025 21:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
Status: PUBLISHED
Assigner: nvidia
Published:
Updated: 2025-06-17T21:09:17.363Z
Reserved: 2023-04-22T02:38:33.414Z
Link: CVE-2023-31036
Updated: 2025-06-17T21:07:14.236Z
Status : Modified
Published: 2024-01-12T17:15:09.183
Modified: 2024-11-21T08:01:17.673
Link: CVE-2023-31036
No data.
OpenCVE Enrichment
No data.
EUVD