Upstream information

CVE-2025-52566 at MITRE

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.

SUSE information

Overall state of this security issue: Does not affect SUSE products

This issue is currently rated as having important severity.

CVSS v3 Scores
  CNA (GitHub) National Vulnerability Database SUSE
Base Score 8.6 8.8 8.6
Vector CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Attack Vector Local Network Local
Attack Complexity Low Low Low
Privileges Required None None None
User Interaction Required Required Required
Scope Changed Unchanged Changed
Confidentiality Impact High High High
Integrity Impact High High High
Availability Impact High High High
CVSSv3 Version 3.1 3.1 3.1
SUSE Bugzilla entry: 1245328 [NEW]

No SUSE Security Announcements cross referenced.


SUSE Timeline for this CVE

CVE page created: Tue Jun 24 20:00:45 2025
CVE page last modified: Thu Aug 28 14:18:33 2025