What’s Vulnerable › Vulnerabilities

CVE-2026-33298: llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

• Severity: high (CVSS 7.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.5% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2026-03-24 · updated 2026-06-17
• Weakness: CWE-122

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.

Affected products

• ggml-org llama.cpp: before b7824 — fixed in b7824

How to fix

Upgrade to a fixed version: ggml-org llama.cpp b7824. Check the vendor advisory for mitigations.

References

• https://github.com/ggml-org/llama.cpp/releases/tag/b7824
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7

Get alerted when CVE-2026-33298 or the next vulnerability affects your stack