CVE-2026-27940

HIGH

7.8

Description

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.

CVE Details

CVSS v3.1 Score7.8

SeverityHIGH

CVSS VectorCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack VectorLOCAL

ComplexityLOW

Privileges RequiredNONE

User InteractionREQUIRED

Published3/12/2026

Last Modified3/12/2026

Sourcenvd

Honeypot Sightings0

Weaknesses (CWE)

CWE-122CWE-190

References

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.