NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
🛡️
Not in CISA KEV
HIGH severity

CVE-2026-133710 — Ggml-org

HIGHFix: ggml-org/llama.cpp@50518b6

CVE-2026-133710 is a high-severity (CVSS 7.8) CWE-190 vulnerability. The records list no fixed version yet; check the vendor advisory below and apply the mitigations in the meantime.

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.…

Published
Updated
Affected
—
Patched
See advisory
Exploits
None indexed
Exploitation data as of Nov 20, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

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.

Detection & mitigation playbook

Vulnerability
  1. Detect

    Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`).

  2. Remediation status

    The records we use list no fixed release for CVE-2026-133710. Check the upstream advisory for a patched version, and apply the exposure-reduction steps below in the meantime.

  3. Mitigate without a patch

    Constrain what reaches the vulnerable code: limit the size and shape of untrusted input, isolate the affected component in a sandboxed or least-privileged process, and enable the platform's memory-safety mitigations (ASLR, stack protector, hardened allocator) so an out-of-bounds access is more likely to fail closed than to be exploitable.

Frequently Asked Questions

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.
O3 Security · Impact-Aware SCA

Is CVE-2026-133710 in your dependencies?

Find it across your dependency tree, including transitive dependencies.