Critical severity · published Nov 21, 2025
CVE-2025-62608
MLX has heap-buffer-overflow in load()
9.1
CVSS
0.6%
EPSS
No
On KEV
Description
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a heap buffer overflow in mlx::core::load() when parsing malicious NumPy .npy files. Attacker-controlled file causes 13-byte out-of-bounds read, leading to crash or information disclosure. This issue has been patched in version 0.29.4.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 47% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
ML
mlx · ml-explore
< 0.29.4 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-62608
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-62608
Issue Tracking
https://github.com/ml-explore/mlx/pull/1
Issue Tracking
https://github.com/ml-explore/mlx/pull/2
Exploit
https://github.com/ml-explore/mlx/security/advisories/GHSA-w6vg-jg77-2qg6
More from mlx
7.5
CVE-2025-62609
MLX has Wild Pointer Dereference in load_gguf()
