EUVD-2026-19751
GHSA-j364-q6wp-mwj2
Severity by source
AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:L
Primary rating from NVD · only source for this CVE.
CVSS VectorNVD
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:L
Lifecycle Timeline
3DescriptionCVE.org
NVIDIA Triton Inference Server contains a vulnerability in triton server where an attacker may cause an information disclosure by uploading a model configuration. A successful exploit of this vulnerability may lead to information disclosure or denial of service.
AnalysisAI
NVIDIA Triton Inference Server prior to r26.02 allows unauthenticated remote attackers to trigger information disclosure and denial of service through malicious model configuration uploads, exploiting a path traversal vulnerability (CWE-22) that enables access to sensitive files outside intended directories. The CVSS 4.8 score reflects moderate risk with high attack complexity, though real-world exploitation likelihood depends on network accessibility to model upload endpoints.
Technical ContextAI
The vulnerability resides in NVIDIA's Triton Inference Server, an open-source inference platform used for deploying machine learning models at scale. The root cause is a path traversal flaw (CWE-22) in the model configuration upload handler that fails to properly validate or sanitize file paths before processing. When processing model configurations, the server does not adequately restrict path traversal sequences (such as '../'), allowing an attacker to reference files outside the intended model directory hierarchy. This affects the inference server's model repository management functionality, which is critical for loading and managing models. The vulnerability impacts all versions of the CPE:2.3:a:nvidia:triton_inference_server prior to the patched release.
RemediationAI
Upgrade NVIDIA Triton Inference Server to version r26.02 or later, which includes the vendor-released patch addressing the path traversal vulnerability. For organizations unable to upgrade immediately, restrict network access to the model upload endpoint through firewall rules or network segmentation, limiting exposure to trusted administrative networks only. Validate and sanitize all model configuration files before deployment, and review server logs for unusual model upload activity. For detailed remediation guidance and patch verification, consult the official NVIDIA advisory at https://nvidia.custhelp.com/app/answers/detail/a_id/5816.
The NVIDIA driver in the Graphics Drivers subsystem in Apple OS X before 10.11.4 allows attackers to execute arbitrary c
The NVIDIA driver before 307.78, and Release 310 before 311.00, in the NVIDIA Display Driver service on Windows does not
NVIDIA Windows GPU Display Driver (all versions) contains a vulnerability in DirectX drivers, in which a specially craft
Authentication bypass in NVIDIA Triton Inference Server allows unauthenticated remote attackers to reach protected funct
NVIDIA Windows GPU Display Driver (all versions) contains a vulnerability in DirectX drivers, in which a specially craft
NVIDIA Container Toolkit for Linux contains a Time-of-Check Time-of-Use (TOCTOU) vulnerability when used with default co
For the NVIDIA Quadro, NVS, and GeForce products, NVIDIA GeForce Experience R340 before GFE 2.11.4.125 and R375 before G
The NVIDIA Graphics Drivers subsystem in Apple OS X before 10.11.5 allows attackers to execute arbitrary code in a privi
NVIDIA Container Toolkit 1.16.1 or earlier contains a Time-of-check Time-of-Use (TOCTOU) vulnerability when used with de
The nvCommandQueue::GetHandleIndex method in the NVIDIA Graphics Drivers subsystem in Apple OS X before 10.11.5 allows a
nvSCPAPISvr.exe in the Stereoscopic 3D Driver Service in the NVIDIA GPU graphics driver R340 before 341.92, R352 before
For the NVIDIA Quadro, NVS, and GeForce products, NVIDIA Windows GPU Display Driver R340 before 342.00 and R375 before 3
Same weakness CWE-22 – Path Traversal
View allSame technique Information Disclosure
View allShare
External POC / Exploit Code
Leaving vuln.today