← Database

CVE-2024-42477

MEDIUM CVSS: 5.3 Published: 2024-08-12 Modified: 2026-06-17

Description

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.

Affected Platforms

Ggml Llama.Cpp

Weakness Type

CWE-125, CWE-401

References