CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

Medium 6.9 Published 27 Oct 2026 Updated 27 Oct 2026

Exploited in the wild: Not known
Fix: None listed

What is CVE-2024-58399?

CVE-2024-58399 is a medium-severity vulnerability in ggml-org llama.cpp, published on 27 Oct 2026.

Official 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.

Weakness: CWE-125

Which versions are affected by CVE-2024-58399?

How do I fix CVE-2024-58399?

No fix has been published for CVE-2024-58399 yet. Limit exposure of the affected software until one is available.

Is CVE-2024-58399 being exploited?

There is no known exploitation of CVE-2024-58399 in the wild and no public exploit code.

Sources

Also known as GHSA-xf8w-pfxh-7xj3, UBUNTU-CVE-2024-58399.