A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing 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.
References
| Link | Resource |
|---|---|
| https://talosintelligence.com/vulnerability_reports/TALOS-2024-1912 | Exploit Third Party Advisory |
| https://talosintelligence.com/vulnerability_reports/TALOS-2024-1912 | Exploit Third Party Advisory |
| https://www.talosintelligence.com/vulnerability_reports/TALOS-2024-1912 |
Configurations
History
04 Nov 2025, 19:16
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
Information
Published : 2024-02-26 16:27
Updated : 2025-11-04 19:16
NVD link : CVE-2024-21825
Mitre link : CVE-2024-21825
CVE.ORG link : CVE-2024-21825
JSON object : View
Products Affected
ggerganov
- llama.cpp
