CVE-2024-58399

EUVD-2024-55826
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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTPrimary
6.1 MEDIUM
LOCAL
LOW
NONE
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
Awaiting analysis
This vulnerability is currently awaiting analysis.
Base Score
CVSS 3.x
EPSS Score
Percentile: 1.83%
Common Weakness Enumeration
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
https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets