CVE-2023-31036

CVE

Published Jan 12, 2024 CVSS 3.1 · 7.5 High EPSS < 1% KEV · Not listed
Description
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
EUVD EUVD EUVD-2023-35373 NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
nvidia
Published
Updated
Jun 17, 2025, 9:09 PM
Reserved
Apr 22, 2023, 2:38 AM
Status
Modified
Published
Jan 12, 2024, 5:15 PM
Modified
Jun 17, 2026, 5:56 AM