Buffer overflow in Ggml Llama.cpp

CVE-2026-34159

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.

Vulnerability class: Buffer Overflow

Published · last modified .

CVSS v3 metric

CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS 0.016, 76.5th percentile (scored ); unchanged over 30 days. About EPSS.

Affected products

Weakness classification (CWE)

Public exploits and proof-of-concept code

3 public repositories with exploit or proof-of-concept code for this CVE:

References