CVE-2024-42477
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.
- Score
- CVSS 3.1 7.5 High
- Status
- Analyzed - security-advisories@github.com
- Published
- 2024-08-12
- Last modified
- 2024-08-13
- Weaknesses
- CWE-125, CWE-401
Affected products
References
- https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf
