CVE-2025-23320
highpriority · track · 10EPSS 0.010 · 63 %ileexploit · PoCEURUUSEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
exploits (1)
Public proof-of-concept and weaponised exploit code.
- There-was-a-bird/triton-cve-2025-23320There-was-a-bird/triton-cve-2025-23320PoC · poc_in_github
affected products (3)
Products and version ranges known to be affected.
also known as (4)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (9)
External citations — patches, advisories, analysis.
- https://nvd.nist.gov/vuln/detail/CVE-2025-23320cnnvd
- https://nvidia.custhelp.com/app/answers/detail/a_id/5687cnnvd
- https://www.cve.org/CVERecord?id=CVE-2025-23320cnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-23320enisa_euvd
- https://nvidia.custhelp.com/app/answers/detail/a_id/5687enisa_euvd
- https://www.cve.org/CVERecord?id=CVE-2025-23320enisa_euvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-23320US Government Resourcenvd
- https://nvidia.custhelp.com/app/answers/detail/a_id/5687Vendor Advisorynvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan