Integer overflow in Ggml-Org Llama.cpp

CVE-2026-116829

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.

Vulnerability class: Integer Overflow

Published · last modified .

CVSS v3 metric

CVSS v3 base score 6.6 (Medium). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:H.

EPSS exploit prediction

EPSS: 0.001 (2.3th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 2nd percentile — 2.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

The 30-day trend appears once there are two daily scores.

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-116829?
CVE-2026-116829 is a medium-severity vulnerability in Ggml-Org Llama.cpp, classified under Integer Overflow or Wraparound. CVSS score: 6.6/10. Published 2026-10-27.
How severe is CVE-2026-116829?
Medium severity. CVSS v3 base score is 6.6 out of 10.