llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
Résumé
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
Description d'origine
La description telle que publiée par la source (souvent en anglais).
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.
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
État des correctifs par distribution
Paquets corrigés publiés par chaque distribution pour cette CVE
- Debian DEBIAN-CVE-2026-34159 llama.cpp Corrigé dans: 8611+dfsg-1
- Ubuntu UBUNTU-CVE-2026-34159 llama.cpp
Références
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com
- patch github.com