🛡️ CVE-2025-53630

⚪ Unknown ✅ No Known Exploit CWE-122 NVD
N/A
CVSS Score
0 Low4 Medium7 High9 Critical10

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.

Weakness class

CVE-2025-53630 is classified as CWE-122: Heap-based Buffer Overflow. A write past the end of a heap allocation corrupts allocator metadata or neighbouring objects.

Affected software

CVE-2025-53630 is recorded against 1 package.

  • unknown

Timeline and source

Published on 10 July 2025 and last revised on 17 June 2026. No public exploit is currently recorded for this entry. Record sourced from NVD.

References

github.com
github.com

CVE-2025-53630 on other distributions

Each distribution ships its own build and its own fixed version. Pick the one you run:

Details

Severity Unknown
CVSS Score N/A
CVSS Vector N/A
CWE CWE-122
Public Exploit ✅ No
Source NVD
Published 2025-07-10
Updated 2026-08-11
Modified 2026-06-17
Fix URL N/A

Affected Packages

Software From version Fixed in
unknown — —

Similar Threats

Free Vulnerability Check

Is your site affected by CVE-2025-53630?

BotEraser helps you identify potentially vulnerable plugins and themes by checking your installation against CVE-2025-53630 and other known CVE records.

Scan My Site Free →

No credit card required  ·  Results in minutes

ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.