llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp存在安全漏洞,该漏洞源于 rpc_tensor 结构体中的 data 指针可导致任意地址读取。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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-2024-42479 | 10.0 CRITICAL | llama.cpp allows write-what-where in rpc_server::set_tensor |
| CVE-2024-42477 | 5.3 MEDIUM | llama.cpp global-buffer-overflow in ggml_type_size |
No comments yet