CVE-2026-126974

llama.cpp GGUF integer overflow could execute code

llama.cpp · llama.cpp

First documented disclosure · Review checkpoint

Summary

Opening a malicious model artifact could execute code in the model-loading process.

Severity and exploitation evidence

High · 7.8/10 · CVSS 3.0. Severity source.

Exploitation not established: Malicious exploitation remains unverified in the reviewed sources.

Exploitation evidence source

Technical severity is not a measure of observed attacks or of risk to your deployment. Attempts, demonstrations, and successful compromise retain the qualifications in the source.

How the weakness works

Unchecked GGUF values could overflow an integer before a memory write.

Conditions required

A user opens an attacker-controlled GGUF artifact in an affected build.

Potential impact

Code can run with the current process’s permissions.

Affected versions and configurations

b11160 (70c4e1582) is confirmed affected; the full range is unspecified.

Fix and mitigation status

Merged correction cf24317bea431b807dc93319d74c61bed6e20aff (PR 31336). A first packaged fixed build is unverified.

Practical next steps

Deploy a build verified to include the linked correction and load only trusted model artifacts.

Operating lesson

Treat model files as untrusted parser inputs requiring bounds and overflow checks.

Evidence and limits

The public correction PR opened October 28 and explicitly describes two out-of-bounds writes and their bounds checks. ZDI’s formal advisory followed November 13; the CVE record was published November 17. ZDI supplies CVSS 3.0 and links this correction. The CNA confirms a tested build, not an exhaustive version interval.

Sources