Back to Database
Status published
High
CVE-2025-23320
NVIDIA Triton Inference Server for Windows and Linux contains a...
Vulnerability Description
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure.
Impact Analysis
Refer to official advisory for detailed impact metrics.
Remediation
Ensure systems are updated to the latest vendor-supplied patch levels.
THREAT MONITOR
Am I Vulnerable?
Launch our assessment wizard to check if your infrastructure is exposed to • CVE-2025-23320
Credits & Attribution
No credits recorded in the NVD database.
References
More from NVIDIA
View All →CVE-2025-33255
NVIDIA TRT-LLM for any platform contains a vulnerability in MPI...
High
7.5
CVE-2025-33254
NVIDIA Triton Inference Server contains a vulnerability where an attacker...
High
7.5
CVE-2025-33253
NVIDIA NeMo Framework contains a vulnerability where an attacker could...
High
7.8
CVE-2025-33252
NVIDIA NeMo Framework contains a vulnerability where an attacker could...
High
7.8
CVE-2025-33251
NVIDIA NeMo Framework contains a vulnerability where an attacker could...
High
7.8
Affected Vendor
NVIDIA
View all reports →Affected Software
Triton Inference Server
Vulnerable Versions:
All versions prior to 25.07
Timeline
Official Publish:
August 6th, 2025
Last Modified:
August 6th, 2025
Added to House:
July 22nd, 2026
CVSS Vectors
V3:
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N