| ID |
CVE-2026-34159
|
| Sažetak |
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492. |
| Reference |
|
| CVSS |
| Base: | 9.8 |
| Impact: | 5.9 |
| Exploitability: | 3.9 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
NONE |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| HIGH |
HIGH |
HIGH |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Zadnje važnije ažuriranje |
03-04-2026 - 16:10 |
| Objavljeno |
01-04-2026 - 18:16 |
