CVE-2025-53630CWE-122CWE-680

Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf

High · published July 10, 2025

CVSS v4.0
8.9
EPSS
0%
Percentile
28.9
In the wild
Unconfirmed
What it is

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.

The record
Technical detail
CVSS v4.0
8.9 · HIGH
Vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P
EPSS
0.00363 · 28.9th percentile
Weaknesses
CWE-122 · Heap-based Buffer Overflow; CWE-680 · Integer Overflow to Buffer Overflow
Published
2025-07-10T19:32Z
EPSS history
Timeline
  • 10 JUL 19:32Z
    Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
    cvelistv5