CVE-2026-65119
Received Received - Intake

KvCache-Aware Router Tokenizer Loading Flaw in NVIDIA TensorRT-LLM

Publication date: 2026-10-27

Last updated on: 2026-10-27

Assigner: NVIDIA Corporation

Description
NVIDIA TensorRT-LLM for any platform contains a vulnerability in KvCacheAwareRouter tokenizer loading, where an attacker could cause inclusion of functionality from an untrusted control sphere. A successful exploit might lead to code execution, information disclosure, data tampering, and denial of service.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-10-27
Last Modified
2026-10-27
Generated
2026-10-27
AI Q&A
2026-10-27
EPSS Evaluated
N/A
NVD
CVE-2026-65119
EUVD
EUVD-2026-110820

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
NVIDIA TensorRT-LLM 1.3.0rc24

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-829 The product imports, requires, or includes executable functionality (such as a library) from a source that is outside of the intended control sphere.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in NVIDIA TensorRT-LLM allows an attacker to include functionality from an untrusted source during tokenizer loading. This could lead to code execution, information disclosure, data tampering, or denial of service if exploited.

Impact Analysis

If exploited, this vulnerability could allow attackers to execute arbitrary code, steal sensitive information, alter data, or disrupt services running on systems using TensorRT-LLM.

Mitigation Strategies

Update NVIDIA TensorRT-LLM to the latest patched version to address the KvCacheAwareRouter tokenizer loading vulnerability. Monitor NVIDIA's security bulletins for updates and apply patches promptly.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-65119. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart