Vulnerability · Published Oct 27, 2026 · Assigned by VulnCheck

CVE-2026-116829llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader

Medium 6.6

In plain English

A medium-severity integer 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 0.1% (higher than 2% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.6Medium

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

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	1:0.6.0+dfsg-1	DEBIAN-CVE-2026-116829
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-116829
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-116829

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	b10398 – before b113010.1.0 – before 0.6.0

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

References

https://github.com/ggml-org/llama.cpp/issues/29383 issue-tracking
https://github.com/ggml-org/llama.cpp/pull/29384 patch, issue-tracking
https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7ed9fc patch
https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701 technical-description
llama.cpp b11301 Release Notes release-notes
VulnCheck Advisory: llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader third-party-advisory