CVE-2024-42477CWE-125

llama.cpp global-buffer-overflow in ggml_type_size

Medium · published August 12, 2024

CVSS v3.1
5.3
EPSS
0%
Percentile
38.6
In the wild
Unconfirmed
What it is

llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

The record
Technical detail
CVSS v3.1
5.3 · MEDIUM
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
CVSS v4.0
Not supplied
EPSS
0.00456 · 38.6th percentile
Weakness
CWE-125 · Out-of-bounds Read
Published
2024-08-12T15:02Z
EPSS history
Timeline
  • 12 AUG 15:02Z
    llama.cpp global-buffer-overflow in ggml_type_size
    cvelistv5