HighVulnerability

CVE-2026-31219: optimate insecure deserialization in _load_model() via a crafted model file

Source: NVD(opens in a new tab)
Identifier: CVE-2026-31219
Published: May 12, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

CVE-2026-31219 affects the _load_model() function in the neural_magic_training.py script of the optimate project, as of commit a6d302f912b481c94370811af6b11402f51d377f (2024-07-21). When a user supplies a single model file (.pt or .pth) through the --model argument, the function loads it with torch.load() without setting weights_only=True, allowing arbitrary Python objects to be deserialized via Pickle (CWE-502). A remote attacker who provides a crafted model file can achieve arbitrary code execution on the victim's system.

Mitigation

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

Details

Scores and exploitation

EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 6, 2026.
Disclosure date: May 12, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0010

Classification

Attack type: Supply chain
Attack sophistication: Trivial
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
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-2026-31219

First tracked: May 12, 2026 at 02:07 PM ET, from NVD/CVE Database

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

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items