6.1Medium

CVE-2024-58399llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

ggml-org llama.cpp Published: (24 days ago)

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.

Weakness (CWE): CWE-125

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
ggml llama.cpp b1046 – < b2731
ggml-org llama.cpp b1046 – < b2731

References and patches