CVE-2025-62609

HIGH

MLX < 0.29.4 - Denial of Service via Malicious GGUF File Loading

Title source: llm

Description

MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.

References (1)

Core 1

Core References

Exploit, Third Party Advisory x_refsource_confirm

https://github.com/ml-explore/mlx/security/advisories/GHSA-j842-xgm4-wf88

Scores

CVSS v3 7.5

EPSS 0.0010

EPSS Percentile 27.2%

Attack Vector NETWORK

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

CISA SSVC

Vulnrichment

Exploitation poc

Automatable yes

Technical Impact partial

Details

CWE

CWE-476

Status published

Products (2)

ml-explore/mlx < 0.29.4

pypi/mlx 0 - 0.29.4PyPI

Published Nov 21, 2025

Tracked Since Feb 18, 2026