As blockchain technology becomes more popular, smart contracts are gaining traction in fields like IoT, finance, e-commerce and healthcare. It brings security risks, with vulnerabilities that result in financial losses. Current tools rely on strict rules, which slow down the detection process as contracts grow in complexity. This research evaluates three key traditional tools which uses static analysis and symbolic execution to detect smart contract vulnerabilities. The tools performances and efficiency are evaluated and compared on various performance metrics and a detailed study is presented on it. This study introduces a hybrid deep learning model combining CNNs and transformer features to detect the vulnerabilities. The model utilizes CNN for feature extraction and Transformers for contextual awareness and achieves efficient and accurate vulnerability detection on Ethereum smart contract datasets. Multi-head attention mechanism in transformers enhances its ability to capture diverse features and relationships, which can lead to better generalization and performance. The results prove that the model performs better in efficiency through various performance metrics such as accuracy, precision, recall, runtime thereby enhancing the overall security of blockchain network. Additionally, this research emphasize the importance of smart contracts in web3 E-commerce by deploying a decentralized network. Experiments were conducted on how the smart contract is deployed and vulnerabilities are detected to have better understanding on the backend of the efficient blockchain network. A real time detection and mitigation of vulnerabilities through alert system has been observed and recorded.