CVE-2026-33298 | BDVDB-2026-322296 Detail

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#

Weaknesses#

References#

Exploit#

History#

1. Version 12026-03-24Record published in the CVE List.
2. Version 22026-03-25Most recent update recorded in the CVE List.