Vulnerability · Published Mar 24, 2026 · Assigned by GitHub_M

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

High 7.8

In plain English

A high-severity heap buffer overflow in llama.cpp from ggml-org. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 43% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.8High

Exploit odds (30 days)0.5%top 57.3% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	7965+dfsg-1	DEBIAN-CVE-2026-33298
Ubuntu:25.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-33298
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-33298
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-33298

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	< b7824

Weakness: CWE-122, CWE-190 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

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