CVE-2026-33298: 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…

PriorityP345high7.8CVSS 3.1

AVLACLPRNUIRSUCHIHAH

EPSS

0.48%

37.6th percentile

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

3 ranges

Vendor	Product	Version range	Fixed in
debian	llama.cpp	< llama.cpp 7965+dfsg-1 (sid)	llama.cpp 7965+dfsg-1 (sid)
ggml-org	llama.cpp	< b7824	b7824
ggml	llama.cpp	< b7824	b7824

CVSS provenance

nvdv3.17.8HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

osv7.8HIGH

vendor_debian7.8HIGH

Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.