CVE-2026-33298
7.8 · HIGHOverview
CVE-2026-33298 is a high-severity vulnerability affecting ggml llama.cpp. It was published on March 24, 2026 and has a CVSS 3.1 base score of 7.8 (HIGH).
This vulnerability has a CVSS 3.1 base score of 7.8, rated HIGH. It requires local or adjacent network access to exploit. No authentication or special privileges are required for exploitation.
Technical 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.
Remediation
Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|---|---|---|
| ggml | llama.cpp | >= 0, < b7824 | Affected |
Frequently Asked Questions
What is CVE-2026-33298?
CVE-2026-33298 is a high-severity vulnerability affecting ggml llama.cpp. It was published on March 24, 2026 and has a CVSS 3.1 base score of 7.8 (HIGH).
How severe is CVE-2026-33298?
This vulnerability has a CVSS 3.1 base score of 7.8, rated HIGH. It requires local or adjacent network access to exploit. No authentication or special privileges are required for exploitation.
How do I fix or remediate CVE-2026-33298?
Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2026-33298?
CyberStrike's AI-powered security agents can automatically detect CVE-2026-33298 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related HIGH CVEs from 2026
View all →H3 is a minimal H(TTP) framework built for high performance and portability. Prior to 1.15.5, there
OpenProject is an open-source, web-based project management software. To enable the real time collab
OpenSift is an AI study tool that sifts through large datasets using semantic search and generative
Budibase is a low code platform for creating internal tools, workflows, and admin panels. In 3.24.0
FileBrowser Quantum is a free, self-hosted, web-based file manager. Prior to 1.3.1-beta and 1.2.2-st
Shopware is an open commerce platform. Prior to 6.6.10.15 and 6.7.8.1, a vulnerability in the Shopwa
ChurchCRM is an open-source church management system. Prior to 7.1.0, a stored cross-site scripting
A Stored Cross-Site Scripting vulnerability was discovered in the Assets and Nodes functionality due
Postiz is an AI social media scheduling tool. Prior to version 2.21.6, a file upload validation bypa
A server-side request forgery (SSRF) vulnerability was identified in GitHub Enterprise Server that a
Cross-Site Scripting (XSS) vulnerability exists in HTMLy version 3.1.1 in the content creation funct
An Improper Certificate Validation in Ivanti EPMM before versions 12.6.1.1, 12.7.0.1, and 12.8.0.1 a