CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
llama.cpp tokenizer signed vs. unsigned heap overflow
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.
Reserved 2025-06-18 | Published 2025-06-24 | Updated 2025-06-24 | Assigner GitHub_MCWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer
CWE-195: Signed to Unsigned Conversion Error
github.com/...ma.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
github.com/...ommit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af
Support options
