QwikSec

Security Database

CVE

CWE

Training

CVE-2025-53630

Published: Jul 10, 2025

Modified: Jul 10, 2025

PUBLISHED

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.

Vendor	Product	Versions
ggml-org	llama.cpp	affected `< 26a48ad699d50b6268900062661bd22f3e792579`

Weaknesses (CWE)

References

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8

x_refsource_CONFIRM

https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579

x_refsource_MISC

Security Training

Train your team to recognize and prevent security threats with our comprehensive security awareness program.

Vulnerability Scanning

Discover vulnerabilities in your applications and infrastructure before attackers do.