Buffer overflow in Ggml-Org Llama.cpp
CVE-2025-53630
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.
Vulnerability class: Buffer Overflow
Published · last modified .
EPSS exploit prediction
EPSS: 0.003 (22.3th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 22nd percentile — 22.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: 0.000
Affected products
- Ggml-Org Llama.cpp — versions < 26a48ad699d50b6268900062661bd22f3e792579