CVE-2024-58399Published Oct 27, 2026 · Oct 27Updated Nov 4
llama.cpp out-of-bounds read in GGUF tensor offset handling
ggml-org llama.cpp
Medium6.9Fix available
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| ggml-org llama.cpp |
| No fix yet |
Original 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.
From the CVE record · VulnCheck