VYPR
High severity7.8NVD Advisory· Published Mar 12, 2026· Updated Apr 28, 2026

CVE-2026-27940

CVE-2026-27940

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

2
  • Ggml/Llama.cpp2 versions
    cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*+ 1 more
    • cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*range: <b8146
    • (no CPE)range: < b8146

Patches

Vulnerability mechanics

References

1

News mentions

0

No linked articles in our index yet.