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.
PoC: CVE-2026-34159-Vulnerability-Research-Analysis-Detection
Critical buffer validation bypass in deserialize_tensor() (llama.cpp < b8492). Null tensor buffer skips bounds check, enabling unauthenticated arbitrary R/W via GRAPH_COMPUTE. ASLR bypass + RCE over TCP 50052.
PoC: CVE-2026-34159
0 Click RCE exploit for CVE-2026-34159 Lama.cpp RPC server
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Get alerted for CVEs like this
Register your stack and get notified within minutes when a matching CVE drops.
Start monitoring free