CVE-2024-21825: Integer Overflow
First published: Mon Feb 26 2024(Updated: )
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.
Credit: talos-cna@cisco.com
| Affected Software | Affected Version | How to fix |
|---|---|---|
| Llama.cpp | <2024-01-09 | |
| llama.cpp |
Never miss a vulnerability like this again
Sign up to SecAlerts for real-time vulnerability data matched to your software, aggregated from hundreds of sources.
Frequently Asked Questions
What is the severity of CVE-2024-21825?
CVE-2024-21825 is classified as a critical vulnerability due to its potential to lead to arbitrary code execution.
How do I fix CVE-2024-21825?
To fix CVE-2024-21825, update the llama.cpp GGUF library to a version released after January 9, 2024.
What causes the CVE-2024-21825 vulnerability?
CVE-2024-21825 is caused by a heap-based buffer overflow in the GGUF library's parsing functionalities.
Who is affected by CVE-2024-21825?
Users of the llama.cpp GGUF library prior to the patch released after January 9, 2024, are affected by CVE-2024-21825.
What type of vulnerability is CVE-2024-21825?
CVE-2024-21825 is a heap-based buffer overflow vulnerability.
- agent/references
- agent/first-publish-date
- agent/type
- agent/description
- agent/author
- collector/mitre-cve
- source/MITRE
- agent/source
- agent/weakness
- agent/last-modified-date
- agent/severity
- agent/event
- collector/nvd-api
- source/NVD
- agent/software-canonical-lookup
- agent/software-canonical-lookup-request
- agent/tags
- agent/softwarecombine
- agent/guess-ai
- vendor/ggerganov
- canonical/llama.cpp
- vendor/llama.cpp