7.5
CVE-2025-23320
- EPSS 0.07%
- Published 06.08.2025 12:37:43
- Last modified 12.08.2025 16:34:52
- Source psirt@nvidia.com
- Teams watchlist Login
- Open Login
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.
Verknüpft mit AI von unstrukturierten Daten zu bestehenden CPE der NVD
This information is available to logged-in users. Login
Data is provided by the National Vulnerability Database (NVD)
Nvidia ≫ Triton Inference Server Version < 25.07
Zu dieser CVE wurde keine CISA KEV oder CERT.AT-Warnung gefunden.
Type | Source | Score | Percentile |
---|---|---|---|
EPSS | FIRST.org | 0.07% | 0.219 |
Source | Base Score | Exploit Score | Impact Score | Vector string |
---|---|---|---|---|
psirt@nvidia.com | 7.5 | 3.9 | 3.6 |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
|
CWE-209 Generation of Error Message Containing Sensitive Information
The product generates an error message that includes sensitive information about its environment, users, or associated data.