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://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets

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

https://github.com/ggml-org/llama.cpp/pull/6885

https://github.com/ggml-org/llama.cpp/issues/6774

https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d

https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004

https://euvd.enisa.europa.eu/vulnerability/EUVD-2024-55826

Details

Source: Mitre, NVD

Risk Information

CVSS v2

CVSS v3

CVSS v4

EPSS