HIGH · 7.8

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 G...

Vulnerability 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.

CVSS Score

7.8

HIGH

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH

Affected Products

VendorProductVersions
GgmlLlama.Cpp< b7824

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-33298?

CVE-2026-33298 is a vulnerability with a CVSS score of 7.8 (HIGH). 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 G...

How severe is CVE-2026-33298?

CVE-2026-33298 has been rated HIGH with a CVSS base score of 7.8/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-33298?

Check the references section above for vendor advisories and patch information. Affected products include: Ggml Llama.Cpp.