CVE & CISA-KEV Catalog

CVE-2025-53630

UNSCORED

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.

How to fix

Remediation Available
ggmlDebian
Fixed in:0.0~git20250711.b6d2ebd-1CVE-2025-53630

Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.

CVSS v3.1 Vector

No CVSS vector data available.

Exploit Intelligence

0.32%probability of exploitation in 30 days
24thpercentile

Low risk: more likely to be exploited than 24% of all known CVEs.

References

Other references2
Embed a live status badge for CVE-2025-53630
CVE-2025-53630 severity badge

Markdown

[![CVE-2025-53630](https://tridentstack.com/cve/badge/CVE-2025-53630.svg)](https://tridentstack.com/cve/CVE-2025-53630)

HTML

<a href="https://tridentstack.com/cve/CVE-2025-53630"><img src="https://tridentstack.com/cve/badge/CVE-2025-53630.svg" alt="CVE-2025-53630"></a>

Find and fix vulnerabilities across your fleet

TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.

Start free

This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2025-07-15.