Website security is of paramount importance in today's digital landscape, where cyber threats pose a constant challenge. Vulnerability scanning plays a critical role in identifying and mitigating potential risks. In this paper, we introduce a novel approach that combines a Naive Bayes (NB) classifier with a Neural Network (NN) to enhance the accuracy and efficiency of vulnerability scanning. Our proposed hybrid method achieves a remarkable scanning time of 2.13, significantly reducing the time required for comprehensive security assessments. We demonstrate the effectiveness of our approach by performing four types of scanning, including tests for SQL injection, Cross-Site Scripting (XSS), and other vulnerabilities. Through rigorous evaluation and real-world testing, we validate the superior performance of our hybrid NB+NN method in identifying vulnerabilities, providing a robust solution to bolster website security in an increasingly threat-prone environment.