CVE-2026-27940

llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix

State: Published
Severity: 7.8 High
Published: Mar 12, 2026
Updated: Mar 14, 2026
Reserved: Feb 25, 2026

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.

Scores

CVSS	Score	Vector	Source
3.1	7.8 High	CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H	GitHub_M

Weaknesses

CWE-122 Heap-based Buffer Overflow
CWE-190 Integer Overflow or Wraparound

Affected Products

Product	Versions
llama.cppggml-org	< b8146Affected

References

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

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.