CVE-2024-42477
llama.cpp global-buffer-overflow in ggml_type_size
概要
llama.cpp global-buffer-overflow in ggml_type_size
原文の説明
取得元が公開している説明をそのまま載せています (多くは英語)。
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.
出典: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
参照URL
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com