This Skin cancer remains a significant global health concern, with rising cases attributed to prolonged ultraviolet (UV) radiation exposure, environmental changes, and lifestyle factors. Early detection is essential for improving survival rates and treatment effectiveness. This study presents an AI-driven approach for automated skin cancer detection using the CNN deep learning model, which analyzes dermoscopic images to classify skin lesions as benign or malignant. The proposed system follows a structured pipeline, beginning with image acquisition and preprocessing to enhance clarity and standardize input data. The CNN model, pre-trained on large image datasets, extracts deep features from skin lesion images, leveraging its hierarchical learning capabilities to identify patterns associated with malignancy. The classification process assigns probability scores, aiding in risk assessment and early intervention. To evaluate performance, the model was trained and tested on a publicly available dataset, with accuracy, sensitivity, and specificity as key evaluation metrics. Results demonstrate that CNN achieves high classification accuracy, making it a reliable tool for assisting healthcare professionals in preliminary screenings. The study also discusses challenges such as dataset biases, real-world generalization, and clinical integration, emphasizing the need for further optimization. By enhancing diagnostic precision and accessibility, this research contributes to the development of AI-powered tools for early skin cancer detection, supporting both medical practitioners and individuals seeking timely assessments.