CVE-2024-58399

Medium

Description

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.

SeverityMedium

CVSS6.1

Exploit probability—

ProductGgml-org Llama.cpp

PublishedOct 27, 2026

First seenOct 27, 2026

Weakness typeCWE-125Out-of-bounds read

How to fix

Update

ggml-org llama.cppb2731 or later

Patches

Vendor advisories

github.com/ggml-org/llama.cpp/releases/tag/b2731

Affected products

Product	Affected versions	Fixed in
ggml-org llama.cpp	b1046 ≤ v < b2731	b2731

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.