CVE-2024-41130 llama.cpp null pointer dereference in gguf_init_from_file
MediumCVSS 6.5
EPSS 0.34%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: partial
- Technology
- Debian
Description
llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.
Upgrade path
2 packages: 2 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| ggerganov llama.cpp | < b3427; = < b3427 | b3427 | Fixed |
| ggml llama.cpp | < b3427 | b3427 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| ggerganov llama.cpp | = < b3427 | No fix listed |
| ggerganov llama.cpp | < b3427 | b3427 |
| ggml llama.cpp | < b3427 | b3427 |