9.8Critical

CVE-2026-34159llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

ggml-org llama.cpp Published: (7 months ago)

Description

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.

Weakness (CWE): CWE-119

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
ggml llama.cpp < b8492
ggml-org llama.cpp < b8492

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:* < b8492