CVE-2026-34159

[CVE catalog]

Severity

Critical · CVSS 9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Published

Apr 1, 2026, 4:59:59 PM UTC

Source

[NVD] · [CVE record]

EPSS

1.59% · Oct 25, 2026

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. Red Hat Product Security has determined that this vulnerability does not affect any currently supported Red Hat product. This assessment may evolve based on further analysis and discovery. For more information about this vulnerability and the products it affects, please see the linked references. The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.