Phishing attacks remain a significant threat to cybersecurity, targeting individuals and organizations alike. This paper introduces PHISHNET, a comprehensive threat intelligence system that leverages machine learning techniques to detect and mitigate phishing attacks across three communication vectors: URLs, emails, and SMS messages. The system employs Gradient Boosting for URL detection, achieving an accuracy of 98%, while Random Forest algorithms are utilized for email and SMS detection, attaining accuracies of 97% and 96%, respectively. By analyzing various features related to URLs and extracting content from emails and SMS messages, PHISHNET provides users with actionable insights to enhance their security posture against phishing threats.