216.73.216.233

CVE-2025-52566

· Published 24/06/2025 04:15 · Modified 24/06/2025 22:15

Labels: CVE-2025-52566 2025-06-24CVE-2025-52566CWE-119[email protected]

Essential information

Published
24/06/2025 04:15
Modified
24/06/2025 22:15
Author
Creator
CVSS
8.6 HIGH (v3.1)
CISA KEV
No
CWE
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

CVSS metrics

Description

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.

NVD status

Status
Received — CVE has been recently published to the CVE List and has been received by the NVD.
Source
[email protected]
NVD
View on NVD

Affected products (CPE)

ProductCPE
llama cpp / llama cpp cpe:2.3:a:llama_cpp:llama_cpp:*:*:*:*:*:*:*:*

References