Vulnerability · Published Oct 27, 2026 · Assigned by VulnCheck

CVE-2026-116840llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader

Medium 6.1

In plain English

A medium-severity integer overflow in llama.cpp from ggml-org. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 2% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.1Medium

Exploit odds (30 days)0.1%top 97.7% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

llama.cpp b5854 before b11275 contains an integer overflow vulnerability in gguf_init_from_reader that bypasses the CVE-2025-53630 size check when padding near-SIZE_MAX tensor sizes. Attackers can supply a crafted GGUF file whose tensor size pads to zero, causing an undersized data blob and out-of-bounds reads by consumers.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	1:0.6.0+dfsg-1	DEBIAN-CVE-2026-116840
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-116840
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-116840

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	b5854 – before b112750.1.0 – before 0.6.0

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

References

https://github.com/ggml-org/llama.cpp/issues/26978 issue-tracking
https://github.com/ggml-org/llama.cpp/pull/26979 patch, issue-tracking
https://github.com/ggml-org/llama.cpp/commit/a6ea155d3d38b3f6f43d0c0dc29c2d592413ef44 patch
https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L794-L795 technical-description
llama.cpp b11275 Release Notes release-notes
VulnCheck Advisory: llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader third-party-advisory