CVE-2026-133710: llama.cpp b11003 before b12556 Heap Out-of-Bounds Write via hrm_text Model Loader

Published Nov 20, 2026
·
Updated

llama.cpp b11003 before b12556 contains an integer overflow in the hrmtext loader loadarchhparams() 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 loadarchtensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.

Affected Software

1 affected component
ggml-org llama.cpp>=b11003<b12556

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade llama.cpp to a version that resolves this vulnerability.

    Fixed in b12556

Event History

Nov 20, 2026
CVE Published
via MITRE·12:17 PM
Data Sourced
via MITRE·12:17 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·01:18 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are exposed?

Deployments using ggml-org llama.cpp versions from b11003 through b12555 are affected when they load hrm_text GGUF models. The issue is local in the supplied severity vector, but no privileges are required and user interaction is required.

2

What does an attacker need to exploit this?

An attacker needs to cause the target to load a crafted GGUF model containing malicious hrm_text metadata. The layer-factor values are chosen to wrap modulo 2^32, bypassing the loader's block-count check and causing writes beyond model.layers.

3

What should be done if patching is not immediately possible?

Do not load untrusted or externally supplied GGUF models that use the hrm_text architecture. Restrict model ingestion to validated, trusted files until an updated build is deployed.

4

How can I determine whether I may be affected?

Check whether your llama.cpp build is b11003 through b12555 and whether it loads hrm_text GGUF models. Review model sources and ingestion paths for untrusted GGUF files, especially files that can be supplied by users or obtained from external repositories.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203