The World Wide Web has evolved into the web-based application with a greater prone to cyber intrusions. As technology evolves digitally, it becomes much more vulnerable to malicious data that could lead to cyber-attacks. Automated malevolent software, usually known as malware, pose a significant threat to computers and information security linked to the Web with the expansion of the underground digital economy. Malicious URLs are widely used in extortion, malware, as well as other types of cyber-attacks. It’s essential to easily determine phishing URLs. Blacklisting, pattern matching, and regular expressions strategies were implemented in earlier investigations. These methodologies had no effect on identifying the current malware detection versions or completely unique URLs. By implementing a machine learning-based approach, this problem can be eliminated. The detection strategy uses machine learning algorithms like logistic regression, Naive Bayes, decision tree, SVM, random forest, and extreme gradient boosting to assess the accuracy and dependability of this method. Eventually, the findings of the studies illustrated the effectiveness of the proposed method for detection.