CVE-2024-42477
EUVD-2024-3963712.08.2024, 15:15
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.Enginsight
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources.
| Vendor | Product | Version | Source |
|---|---|---|---|
| ggerganov | llama.cpp | 𝑥 < b3561 | ADP |
Common Weakness Enumeration
- CWE-125 - Out-of-bounds ReadThe software reads data past the end, or before the beginning, of the intended buffer.
- CWE-401 - Missing Release of Memory after Effective LifetimeThe software does not sufficiently track and release allocated memory after it has been used, which slowly consumes remaining memory.