Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
At a glance
Severity
HIGH 8.9
EPSS
EPSS 0.36 % · percentile 30 (2026-10-27)
State
PUBLISHED
Published
Updated
Assigner
GitHub_M
NVD status
Deferred
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.
