CVE-2026-34159— llama.cpp 缓冲区错误漏洞

llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

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.

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

内存缓冲区边界内操作的限制不恰当

llama.cpp 缓冲区错误漏洞

llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp b8492之前版本存在缓冲区错误漏洞，该漏洞源于RPC后端的deserialize_tensor()在张量的buffer字段为0时跳过所有边界验证，可能导致未经验证的攻击者通过特制GRAPH_COMPUTE消息读写任意进程内存，结合指针泄露实现完整的ASLR绕过和远程代码执行。

N/A

N/A