Vulnerability · Published Aug 6, 2025 · Assigned by nvidia
CVE-2025-23320
High 7.5
In plain English
A high-severity security flaw in Triton Inference Server from NVIDIA. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 1.0% (higher than 63% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code.
Severity (CVSS 3.1)7.5High
Exploit odds (30 days)1.0%top 37.1% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack tooling1Public PoC
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| NVIDIA | Triton Inference Server | All versions prior to 25.07 |
Weakness: CWE-209 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N