CVE-2025-53630

N/A Unknown
Published: July 10, 2025 Modified: April 15, 2026
View on NVD

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.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory

2 reference(s) from NVD

Quick Stats

CVSS v3 Score
N/A / 10.0
EPSS (Exploit Probability)
0.1%
28th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)