llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 18c2e17之前版本存在输入验证错误漏洞,该漏洞源于GGUF 中的 header.n_kv函数中存在基于堆的缓冲区溢出漏洞,特制的 .gguf 文件可能会导致代码执行。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2024-21836 | 8.8 HIGH | llama.cpp 输入验证错误漏洞 |
| CVE-2024-21802 | 8.8 HIGH | llama.cpp 安全漏洞 |
| CVE-2024-21825 | 8.8 HIGH | llama.cpp 输入验证错误漏洞 |
| CVE-2024-23496 | 8.8 HIGH | llama.cpp 输入验证错误漏洞 |
No comments yet