CVE-2026-27940 — llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix

CVE-2026-27940

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

Description (CNA)

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.

Affected (CNA)

Vendor / product	Versions
ggml-org / llama.cpp	affected < b8146

CWE

CWE-122, CWE-190

References

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

ADP enrichment

CISA-ADP

No English description supplied.

No references supplied.