← Back to search

CVE-2026-65142

7.8 HIGHpublic exploit available

Published 2026-10-06 · Updated 2026-10-07

AI risk analysis

Summary
NVIDIA Model-Optimizer suffers from a deserialization vulnerability that allows attackers to execute arbitrary code by tricking the application into processing untrusted data. This flaw can lead to full system compromise and data exposure.
Exploitability
Exploitation requires user interaction through a maliciously crafted input file, making it moderately difficult but achievable with social engineering or file upload capabilities.
Blast radius
If exploited, this vulnerability could affect any system running NVIDIA Model-Optimizer with access to untrusted model files, potentially leading to widespread code execution across affected environments.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Disable the affected deserialization functionality until a patch is available, or restrict access to the Model-Optimizer service to trusted networks only.
deserializationrcemodel

Analysis generated locally by garnet-coder (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

NVIDIA Model-Optimizer contains a vulnerability where an attacker may cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, data tampering, denial of service, and information disclosure.

CVSS vector

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Weaknesses

CWE-502

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.