CVE-2026-27940: Ggml Llama.cpp

High severity, CVSS 7.8. EPSS: 0.2% chance of exploitation in the next 30 days.

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 products

• Ggml Llama.cpp: before b8146 (fixed in b8146)

Published 2026-03-12. Last modified 2026-06-17.