Integer Overflow or Wraparound Affecting llama.cpp package, versions <1:0.6.0+dfsg-1


Severity

Recommended
0.0
medium
0
10

Snyk's Security Team recommends NVD's CVSS assessment. Learn more

Threat Intelligence

EPSS
0.13% (3rd percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-DEBIAN14-LLAMACPP-21759097
  • published28 Oct 2026
  • disclosed27 Oct 2026

Introduced: 27 Oct 2026

NewCVE-2026-116829  (opens in a new tab)
CWE-190  (opens in a new tab)

How to fix?

Upgrade Debian:14 llama.cpp to version 1:0.6.0+dfsg-1 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream llama.cpp package and not the llama.cpp package as distributed by Debian. See How to fix? for Debian:14 relevant fixed versions and status.

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.

CVSS Base Scores

version 3.1