Vulnerability CVE-2024-42477
Published: 2024-08-12

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.

 References:
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf
https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
Copyright 2026, cxsecurity.com

 

Back to Top