This research evaluates how prompt engineering techniques can significantly improve the security of code generated by large language models (GPT).

• Implemented an automated benchmark to assess various prompt engineering strategies
• Tested multiple techniques using peer-reviewed prompt datasets
• Achieved vulnerability reduction rates of up to 56%
• Demonstrated detection/repair rates of 41%+ for code security issues

These findings are crucial for organizations using AI for code generation, highlighting how carefully engineered prompts can substantially reduce security risks in automated development workflows.

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models