Buffer overflow in Ggml Llama.cpp
CVE-2026-33298
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.
Vulnerability class: Buffer Overflow
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.005, 43.8th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Ggml Llama.cpp
- Ggml-Org Llama.cpp — versions < b7824
Weakness classification (CWE)
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7 (Exploit, Vendor Advisory)
- https://github.com/ggml-org/llama.cpp/releases/tag/b7824 (Release Notes)