CVE-2024-42477 MEDIUM

CVE-2024-42477: llama.cpp global-buffer-overflow in ggml_type_size

Vendor Ggerganov
Product llama.cpp
Weakness CWE-125
Published August 12, 2024
Last update August 13, 2024

CVSS base score

5.3/10
Attack vector Network
Attack complexity Low
Privileges required None
User interaction None
Confidentiality Low
Integrity None

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

What the vulnerability does

01Description

llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Key dates

02Disclosure timeline

August 12, 2024 CVE published
August 13, 2024 Record updated