Not a U.S. government website. NDD is an independent vulnerability database by Volerion and is not affiliated with or endorsed by NIST or NVD.
VOLERION
Volerion Security Research

NOT DEFERRED DATABASE

VULNERABILITIES

CVE-2025-53630 Details

ANALYZED


This CVE record has been analyzed and enriched by NVDAPI.com as an independent party.

Description

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.

Metrics

CVSS 3.x Severity and Vector Strings:

References to Advisories, Solutions, and Tools

By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.

Weakness Enumeration

CWE-IDCWE NameSource
CWE-122Heap-based Buffer Overflow[email protected]
CWE-680Integer Overflow to Buffer Overflow[email protected]

Affected Products

ProductVersions
ggml-org llama.cpp
All versions

CPE

  • No CPEs found in CPE dictionary for this product.

Remediation

  • No remediation found in references.

Change History

3 change records found show changes


QUICK INFO

CVE Dictionary Entry:
CVE-2025-53630
NVD Published Date:
Jul 10, 2025
NVD Last Modified:
Jun 17, 2026
Source:
[email protected]
CVE-2025-53630 Details - Not Deferred