340 matches found
CVE-2024-41130: NULL Pointer Dereference
llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in ggufinitfromfile. This vulnerability is fixed in b3427...
llama.cpp 安全漏洞
llama.cpp is a multimodal model. A denial of service vulnerability exists in llama.cpp that stems from the inclusion of a null pointer dereference in ggufinitfromfile. An attacker could exploit this vulnerability to cause a denial of service...
CVE-2024-32878
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
CVE-2024-32878 Use of Uninitialized Variable Vulnerability in llama.cpp
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
CVE-2024-32878 Use of Uninitialized Variable Vulnerability in llama.cpp
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
CVE-2024-32878
Summary: CVE-2024-32878 affects llama.cpp (C/C++) with a use of an uninitialized heap variable in gguf_init_from_file. The vulnerability can cause a crash (DoS) and may allow arbitrary code execution if an attacker crafts input. The issue has been patched in commit b2740. What’s affected (based o...
CVE-2024-32878 Use of Uninitialized Variable Vulnerability in llama.cpp
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
CVE-2024-32878
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
CVE-2024-32878: Missing Initialization of a Variable
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in ggufinitfromfile, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this...
PT-2024-24933
Name of the Vulnerable Software and Affected Versions Llama.cpp versions prior to the version patched in commit b2740 Description The issue is related to the use of an uninitialized heap variable in the gguf init from file function. This can cause the program to crash, leading to a denial of...
The vulnerability of the header.n_kv function in the llama.cpp file of the GGUF library allows a hacker to execute arbitrary code.
The vulnerability of the header.nkv function in the llama.cpp file of the GGUF library is related to buffer overflow. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code...
CVE-2024-23605
A heap-based buffer overflow vulnerability exists in the GGUF library header.nkv 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...
CVE-2024-21836
A heap-based buffer overflow vulnerability exists in the GGUF library header.ntensors 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...
CVE-2024-21836
A heap-based buffer overflow vulnerability exists in the GGUF library header.ntensors 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...
Heap overflow
A heap-based buffer overflow vulnerability exists in the GGUF library info-ne 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...
Heap overflow
A heap-based buffer overflow vulnerability exists in the GGUF library header.nkv 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...
CVE-2024-21825
A heap-based buffer overflow vulnerability exists in the GGUF library GGUFTYPEARRAY/GGUFTYPESTRING 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...
CVE-2024-21825
Talos details CVE-2024-21825 in llama.cpp (GGUF library) focusing on parsing of GGUF_TYPE_ARRAY/GGUF_TYPE_STRING within gguf_init_from_file. An attacker-provided .gguf file can trigger a heap-based buffer overflow when kv->value.arr.n is large, due to an integer overflow in the allocation kv-&...
CVE-2024-23496
A heap-based buffer overflow vulnerability exists in the GGUF library gguffreadstr 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...
CVE-2024-21836
A heap-based buffer overflow vulnerability exists in the GGUF library header.ntensors 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...