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 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.

Scoring

Severity
HIGH
CVSS base score
8.6
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS probability
0.32%
CWE
CWE-119, CWE-195
Published
2025-06-24
Last modified
2026-03-13

Affected products

Weakness type

Related vulnerabilities

Markdown version · Browse all CVEs