Heap-based buffer overflow in llama.cpp - CVE-2024-21825
Published: February 27, 2024
Vulnerability identifier: #VU86818
CSH Severity: High
CVSSv4.0: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:U/U:Amber
CVE-ID: CVE-2024-21825
CWE-ID: CWE-122
Exploitation vector: Remote access
Exploit availability:
No public exploit available
Vulnerable software:
llama.cpp
llama.cpp
Software vendor:
ggerganov
ggerganov
Description
The vulnerability allows a remote attacker to execute arbitrary code on the target system.
The vulnerability exists due to a boundary error in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing functionality. A remote attacker can trick a victim to open a specially crafted .gguf file, trigger a heap-based buffer overflow and execute arbitrary code on the target system.
Successful exploitation of this vulnerability may result in complete compromise of vulnerable system.
Remediation
Install updates from vendor's website.