CVE-2026-133710

HIGH Status: Awaiting Analysis

CVSS Scores

CVSS v3.x Base Score
7.8
HIGH

Description

llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.

Published
November 20, 2026 1:18 PM
Last Modified
November 20, 2026 1:18 PM
Source
[email protected]

Weaknesses (CWE)

CWE-190

References

Contact Us

Get the CyboWatch SIEM platform, hosting, and 24×7 SOC analysts. Send an enquiry, or call or email us to get started.

Send an enquiry