CVE-2026-33298

CVE-2026-33298 · llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

Cette page présente des faits issus de sources publiques. Consultez l’avis original avant toute mise à jour.

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.

CVSS 7.8 · Élevée · EPSS 0,5% · Correctif disponible

Publication

2026-03-24T00:01:40.989Z

Mise à jour

2026-03-25T03:55:51.679Z

Pile logicielle: system

Vérifiez votre serveur →