CVE-2025-52566

Fixed in a distro release EPSS <1%CVSS 8.6

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.

Published 2025-06-24 · CVE record · OSV

Products: ggml-org llama.cpp

Distro releases