CVE-2024-42477: llama.cpp global-buffer-overflow in ggml_type_size
First published: Mon Aug 12 2024(Updated: )
llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.
Credit: security-advisories@github.com
| Affected Software | Affected Version | How to fix |
|---|---|---|
| Llama.cpp | <b3561 |
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.
Reference Links
Frequently Asked Questions
What is the severity of CVE-2024-42477?
CVE-2024-42477 has a severity rating that indicates it may lead to significant memory data leakage issues.
How do I fix CVE-2024-42477?
To fix CVE-2024-42477, upgrade to version b3561 or later of llama.cpp.
What causes the vulnerability CVE-2024-42477?
CVE-2024-42477 is caused by the unsafe `type` member in the `rpc_tensor` structure that can result in a global buffer overflow.
What is the potential impact of CVE-2024-42477?
The potential impact of CVE-2024-42477 includes memory data leakage, which could expose sensitive information.
Which versions of llama.cpp are affected by CVE-2024-42477?
Versions of llama.cpp prior to b3561 are affected by CVE-2024-42477.
- agent/references
- agent/title
- agent/description
- agent/type
- agent/first-publish-date
- agent/author
- agent/event
- agent/severity
- agent/last-modified-date
- agent/weakness
- agent/remedy
- agent/softwarecombine
- collector/mitre-cve
- source/MITRE
- agent/source
- agent/tags
- collector/nvd-api
- source/NVD
- agent/software-canonical-lookup
- agent/software-canonical-lookup-request
- vendor/ggerganov
- canonical/llama.cpp