cve/2024/CVE-2024-42477.md

CVE-2024-42477

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.

POC

Reference

• b72942fac9
• https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf

Github

• https://github.com/7resp4ss/7resp4ss
• https://github.com/fkie-cad/nvd-json-data-feeds
• https://github.com/honysyang/eleaipoc