Security vulnerabilities in smart contracts are a primary risk for Decentralized Finance (DeFi) and blockchain systems. Current research focuses on detection, neglecting end-to-end automated management. To address this, we propose LLM-BSCVM, an LLM-based framework for automated vulnerability management. We introduce a “Decompose–Retrieve–Generate” methodology that breaks down the workflow into six sub-tasks for specialized agents: detection, repair suggestion, risk assessment, repair, patch verification, and report generation. These agents collaborate in an automated chain, retrieving information from knowledge bases to enhance reasoning. Our evaluation shows LLM-BSCVM achieves an accuracy and F1-score over 91% in detection, comparable to state-of-the-art methods but with a lower false positive rate of 5.0%. Notably, the framework achieves a 53% success rate in automated repair and provides professional audit reports. The project is open-source at: https://github.com/sosol717/LLM-BSCVM .