CVE Daily

CVE-2025-53630

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in th...

High CVSS 8.9

Overview

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.

CWE: CWE-122 Published: 2025-07-10T20:15:27.523
Risk analysis

This vulnerability is rated 🟠 HIGH.

  • CVSS: 8.9 (HIGH)
  • Detected tags: int_overflow, oob_read (tag impact: LOW)

Recommended actions:

  • Prioritize remediation based on business criticality and exposure.
  • Limit exposure and increase monitoring until fixed.

Recommended tools

Tags