NetSight
high8.5

CVE-2026-133710

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 us…

Impact

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.

An attacker can exploit this with local access to the system, without logging in, but a user has to be involved, for example by viewing content. If it succeeds: high risk of data being read, high risk of data or systems being changed, high risk of outages.

Affected products · Ggml-org

ProductAffected versions
Llama.cpp
from b11003 before b12556

Weakness classification

References