MLX has Wild Pointer Dereference in load_gguf()

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS 4.0

5.5 · CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P · score source

EPSS

• CVE-2025-62609: 0.40% estimated exploitation activity in the next 30 days; percentile 34.62 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary Segmentation fault in mlx::core::loadgguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. Environment: - OS: Ubuntu 20.04.6 LTS - Compiler: Clang 19.1.7 Vulnerability Location: mlx/io/gguf.cpp - Function extracttensordata() at lines 59-79 - Vulnerable memcpy at lines 64-67 - Called from loadarrays() at line 177 The Bug: Possible Fix PoC Download the poc file there, or let me know how I can send it to you. AddressSanitizer Output (with instrumented build): Impact - Attack vector: Malicious GGUF file (model weights, typically from untrusted sources) - Affects: MLX users on all platforms who call the vulnerable method with unsanitized input. - Result: Segmentation fault (uncatchable by exception handlers) --- Credits: - Markiyan Melnyk (ARIMLABS) - Mykyta Mudryi (ARIMLABS) - Markiyan Chaklosh (ARIMLABS)

Published by the source

21 Nov 2025, 18:03 UTC

Last modified by the source

6 Jun 2026, 00:45 UTC

Source last checked

26 Oct 2026, 13:44 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-j842-xgm4-wf88

2. Revision 2 · amended · 25 Oct 2026

   Reviewed OSV alias/range/CVSS4 correction; package source scopes and original publication preserved. No customer finding resolved.

3. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-j842-xgm4-wf88

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2025-62609

Advisory: MLX has Wild Pointer Dereference in load_gguf()
IDs: CVE-2025-62609, GHSA-j842-xgm4-wf88
Record: https://patchnext.com/advisories/cve-2025-62609 (revision 3, source checked 26 Oct 2026, 13:44 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 5.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: mlx 0.29.4. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI mlx: affected <= 0.29.3; fixed in 0.29.4

## Suggested inspection (read-only)
- `python -m pip show mlx`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on mlx.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-j842-xgm4-wf88 (OSV record GHSA-j842-xgm4-wf88 lists affected ranges: PyPI mlx >=0 <0.29.4 (fixed))
- Verified: https://github.com/advisories/GHSA-j842-xgm4-wf88 (GitHub-reviewed advisory GHSA-j842-xgm4-wf88 lists affected ranges: PyPI mlx >=0 <=0.29.3)

Commands are suggestions: review each one before running it.