| ID |
CVE-2025-53630
|
| Sažetak |
llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579. |
| Reference |
|
| CVSS |
| Base: | 0.0 |
| Impact: | None |
| Exploitability: | None |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| None |
None |
None |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| None |
None |
None |
|
| CVSS vektor |
None |
| Zadnje važnije ažuriranje |
15-07-2025 - 13:14 |
| Objavljeno |
10-07-2025 - 20:15 |
