CVE coverage
View on NVD →
CVE-2026-133710
CVSS 7.8
no coverage
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.
Detection rules
No detection found — yet
None of Sigma, Elastic, Splunk ESCU, YARA, Microsoft Sentinel, Snort, or Suricata currently has a rule referencing CVE-2026-133710.