Medium severity6.1NVD Advisory· Published Oct 27, 2026
CVE-2024-58399
CVE-2024-58399
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.
Affected products
1Patches
Vulnerability mechanics
References
6- github.com/ggml-org/llama.cpp/blob/b2730/llama.cppnvd
- github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1dnvd
- github.com/ggml-org/llama.cpp/issues/6774nvd
- github.com/ggml-org/llama.cpp/pull/6885nvd
- github.com/ggml-org/llama.cpp/releases/tag/b2731nvd
- www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsetsnvd
News mentions
0No linked articles in our index yet.