This paper explores the potential of Large Language Models (LLMs) in detecting scams, a critical aspect of cybersecurity. Unlike traditional applications, the paper proposes a novel use case for LLMs to identify various types of scams, such as phishing, advance fee fraud, and romance scams. The authors outline the key steps involved in building an effective scam detector using LLMs, including data collection, preprocessing, model selection, training, and integration into target systems. A preliminary evaluation using GPT-3.5 and GPT-4 on a duplicated email demonstrates their proficiency in identifying common signs of phishing or scam emails. However, the paper emphasizes the need for a comprehensive assessment across various language tasks to determine the models' relative strengths and weaknesses. The conclusion highlights the importance of ongoing refinement and collaboration with cybersecurity experts to adapt to evolving threats.This paper explores the potential of Large Language Models (LLMs) in detecting scams, a critical aspect of cybersecurity. Unlike traditional applications, the paper proposes a novel use case for LLMs to identify various types of scams, such as phishing, advance fee fraud, and romance scams. The authors outline the key steps involved in building an effective scam detector using LLMs, including data collection, preprocessing, model selection, training, and integration into target systems. A preliminary evaluation using GPT-3.5 and GPT-4 on a duplicated email demonstrates their proficiency in identifying common signs of phishing or scam emails. However, the paper emphasizes the need for a comprehensive assessment across various language tasks to determine the models' relative strengths and weaknesses. The conclusion highlights the importance of ongoing refinement and collaboration with cybersecurity experts to adapt to evolving threats.