Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

debian логотип

CVE-2026-33298

Опубликовано: 24 мар. 2026
Источник: debian
EPSS Низкий

Описание

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.

Пакеты

ПакетСтатусВерсия исправленияРелизТип
llama.cppfixed7965+dfsg-1package

Примечания

  • https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7

  • https://github.com/ggml-org/llama.cpp/commit/4e5b83b226919c146fbfa754641a6772bcb2d722 (b7824)

EPSS

Процентиль: 39%
0.00477
Низкий

Связанные уязвимости

CVSS3: 7.8
ubuntu
5 месяцев назад

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.

CVSS3: 7.8
nvd
5 месяцев назад

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.

EPSS

Процентиль: 39%
0.00477
Низкий