llama.cpp tokenizer signed vs. unsigned heap overflow
Résumé
llama.cpp tokenizer signed vs. unsigned heap overflow
Description d'origine
La description telle que publiée par la source (souvent en anglais).
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.
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
État des correctifs par distribution
Paquets corrigés publiés par chaque distribution pour cette CVE
- Debian DEBIAN-CVE-2025-52566 llama.cpp Corrigé dans: 5760+dfsg-1
- Ubuntu UBUNTU-CVE-2025-52566 llama.cpp
Références
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com