CVE-2026-27940 - llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
CVE ID :CVE-2026-27940
Published : March 12, 2026, 4:39 p.m. | 49 minutes ago
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.
Severity: 0.0 | NA
Visit the link for more details, such as CVSS details, affected products, timeline, and more...
Published : March 12, 2026, 4:39 p.m. | 49 minutes ago
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.
Severity: 0.0 | NA
Visit the link for more details, such as CVSS details, affected products, timeline, and more...