CVE-2024-41130

Sažetak

llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.

Reference

https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp

CVSS

Base:	5.4
Impact:	2.5
Exploitability:	2.8

Pristup

Vektor	Složenost	Autentikacija
NETWORK	LOW	NONE

Impact

Povjerljivost	Cjelovitost	Dostupnost
NONE	LOW	LOW

CVSS vektor

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L

Zadnje važnije ažuriranje

24-07-2024 - 12:55

Objavljeno

22-07-2024 - 18:15