VULNERABILITY INTELLIGENCE

CVE-2025-53630

EPSS probability0.36%
CISA KEVNot currently listed
Published2025-07-10
Last modified2026-06-17

Description

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.

Weakness classification

  • security-advisories@github.com: CWE-122

Primary references