Home

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.

PUBLISHED Reserved 2026-03-18 | Published 2026-03-24 | Updated 2026-03-25 | Assigner GitHub_M




HIGH: 7.8CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Problem types

CWE-122: Heap-based Buffer Overflow

CWE-190: Integer Overflow or Wraparound

Product status

< b7824
affected

References

github.com/...ma.cpp/security/advisories/GHSA-96jg-mvhq-q7q7

github.com/ggml-org/llama.cpp/releases/tag/b7824

cve.org (CVE-2026-33298)

nvd.nist.gov (CVE-2026-33298)

Download JSON