CVE-2026-33298
Last modified
CVE-2026-33298 is a high-severity vulnerability rated 7.8/10 on the CVSS scale. 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. EPSS estimates a 0.48% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Ggml | Llama.Cpp | < b7824 |
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7Exploit, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-33298?
How severe is CVE-2026-33298?
How do I fix CVE-2026-33298?
Are you affected by CVE-2026-33298?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
