HighVulnerability

CVE-2025-23320: NVIDIA Triton Inference Server Python backend shared memory limit exceeded

Source: NVD(opens in a new tab)
Identifier: CVE-2025-23320
Published: August 6, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.0%

Summary

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend. An attacker could exceed the shared memory limit by sending a very large request, and a successful exploit might lead to information disclosure. The weakness is classified as CWE-209, Generation of Error Message Containing Sensitive Information.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 7.5(high)
EPSS: 1.0%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-209
Attack pattern (CAPEC): CAPEC-54

Affected

Vendors: NVIDIA

Classification

Attack type: Denial of service
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Confidentiality,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-23320

First tracked: February 15, 2026 at 08:45 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

Inference infrastructure

Summary

Mitigation

Topics

Related items