CVE-2024-21836

A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability.
Configurations

Configuration 1 (hide)

cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*

History

12 Feb 2025, 18:53

Type Values Removed Values Added
References () https://talosintelligence.com/vulnerability_reports/TALOS-2024-1915 - () https://talosintelligence.com/vulnerability_reports/TALOS-2024-1915 - Exploit, Third Party Advisory
First Time Ggerganov
Ggerganov llama.cpp
CWE CWE-787
CPE cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*

21 Nov 2024, 08:55

Type Values Removed Values Added
References () https://talosintelligence.com/vulnerability_reports/TALOS-2024-1915 - () https://talosintelligence.com/vulnerability_reports/TALOS-2024-1915 -

26 Feb 2024, 16:32

Type Values Removed Values Added
New CVE

Information

Published : 2024-02-26 16:27

Updated : 2025-02-12 18:53


NVD link : CVE-2024-21836

Mitre link : CVE-2024-21836

CVE.ORG link : CVE-2024-21836


JSON object : View

Products Affected

ggerganov

  • llama.cpp
CWE
CWE-190

Integer Overflow or Wraparound

CWE-787

Out-of-bounds Write