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.

References

• https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004
• https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d
• https://github.com/ggml-org/llama.cpp/issues/6774
• https://github.com/ggml-org/llama.cpp/pull/6885
• https://github.com/ggml-org/llama.cpp/releases/tag/b2731