CVE-2026-33298 Details
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.
An integer overflow vulnerability has been identified in the `ggml_nbytes` function of llama.cpp, an inference library for various LLM models written in C/C++. This vulnerability, present in versions prior to b7824, allows attackers to craft GGUF files with specific tensor dimensions that bypass memory validation. The manipulated tensor dimensions cause the `ggml_nbytes` function to return a drastically reduced size, leading to a heap-based buffer overflow when the application processes the tensor. This memory corruption vulnerability opens the door to potential remote code execution.
Users can update to llama.cpp version b7824 or later, where this vulnerability has been fixed.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Mar 24, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/ggml-org/llama.cpp/releases/tag/b7824 | [email protected] | Release Notes |
| https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7 | [email protected] | ExploitVendor Advisory |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-122 | Heap-based Buffer Overflow | [email protected] |
| CWE-190 | Integer Overflow or Wraparound | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| ggml llama.cpp | < b7824 |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| Apr 30, 2026 | Initial Analysis | [email protected] |
| Mar 24, 2026 | New CVE Received | [email protected] |