CVE-2025-53630
Our Analysis: General-Purpose
Our model has classified this vulnerability as relevant to General-Purpose Systems, helping your team prioritize efforts effectively.
Published Date
July 10, 2025
Last Modified
July 15, 2025
CVSS Vector
Not Available
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.