Monitor vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
7.8
LLM models in C/C++ may write data outside allocated space
CVE-2026-27940
Summary
Some C/C++ code that handles large language model (LLM) models has a bug that could allow an attacker to write data to memory outside the intended space. This could lead to security issues, but it's been fixed in a recent update. To stay secure, make sure you're running the latest version of the affected software.
Original title
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. ...
Original 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.
nvd CVSS3.1
7.8
Vulnerability type
CWE-122
Heap-based Buffer Overflow
CWE-190
Integer Overflow
Published: 12 Mar 2026 · Updated: 14 Mar 2026 · First seen: 12 Mar 2026