Cyber threats are becoming increasingly complex, causing traditional security systems to struggle in keeping up and highlightingthe need for advanced solutions. Large Language Models (LLMs), such as OpenAI’s ChatGPT and Meta AI’s LLaMA, have shown great po-tential to transform cybersecurity workflows with their abilities in natural language understanding, pattern recognition, and automated rea-soning. These models are particularly promising for tasks like network monitoring, threat detection, and security alert triage. However, chal-lenges related to the reliability of outputs, adversarial risks, and ethical concerns must be addressed. This paper presents a comprehensive sur-vey of LLM-based approaches for security testing and evaluates three open-access LLMs, including Mistral-7B, Qwen3-8B, and Llama3.1-8B,demonstrating their ability to enhance security alert analysis. Our findings suggest that LLMs can improve alert clarity and usability, makingthem more accessible to non-experts while providing valuable insights for developers.