CVE-2026-33298
Severity CVSS v4.0:
Pending analysis
Type:
CWE-122
Heap-based Buffer Overflow
Publication date:
24/03/2026
Last modified:
24/03/2026
Description
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.
Impact
Base Score 3.x
7.80
Severity 3.x
HIGH