CVE-2025-52566
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer
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.
HIGH · CVSS 8.6
EPSS 0.00229
Act now
- Public exploit or PoC is available
- CVSS base score ≥ 7.0
Sigma rules0
YARA rules0