# Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models

arXiv: https://arxiv.org/abs/2502.06039 · HTML: https://mlsanity.com/paper/2502.06039/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 10 of 10)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [How Secure is Code Generated by ChatGPT?](https://mlsanity.com/paper/2304.09655/) (2023)
- [LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations](https://mlsanity.com/paper/2303.09384/) (2023)
- [Prompting Techniques for Secure Code Generation: A Systematic Investigation](https://mlsanity.com/paper/2407.07064/) (2024)
- [LLM Security Guard for Code](https://mlsanity.com/paper/2405.01103/) (2024)
- [ChatGPT's Potential in Cryptography Misuse Detection: A Comparative Analysis with Static Analysis Tools](https://mlsanity.com/paper/2409.06561/) (2024)
- [Time to Separate from StackOverflow and Match with ChatGPT for Encryption](https://mlsanity.com/paper/2406.06164/) (2024)

## Built on by (most cited first, 12 of 12)

- [When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?](https://mlsanity.com/paper/2510.17862/) (2025)
- [Security Bug Report Prediction Within and Across Projects: A Comparative Study of BERT and Random Forest](https://mlsanity.com/paper/2504.21037/) (2025)
- [Enhancing Reliability in LLM-Based Secure Code Generation](https://mlsanity.com/paper/2605.24300/) (2026)
- [Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python](https://mlsanity.com/paper/2601.01320/) (2026)
- [Evaluating Large Language Models for Security Bug Report Prediction](https://mlsanity.com/paper/2601.22921/) (2026)
- [Poisoned Source Code Detection in Code Models](https://mlsanity.com/paper/2502.13459/) (2025)
- [A Dataset and Preliminary Study of Using GPT-5 for Code-change Impact Analysis](https://mlsanity.com/paper/2512.19481/) (2025)
- [From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models](https://mlsanity.com/paper/2601.22946/) (2026)
- [A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development](https://mlsanity.com/paper/2604.17763/) (2026)
- [Understanding the Impact of AI Code Assistants on Security API Usage: An Empirical Study](https://mlsanity.com/paper/2607.11348/) (2026)
- [The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting](https://mlsanity.com/paper/2607.23710/) (2026)
- [MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration](https://mlsanity.com/paper/2608.25457/) (2026)

## Abstract (arXiv)

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to automatically assess the impact of various prompt engineering strategies on code security. Our benchmark leverages two peer-reviewed prompt datasets and employs static scanners to evaluate code security at scale. We tested multiple prompt engineering techniques on GPT-3.5-turbo, GPT-4o, and GPT-4o-mini. Our results show that for GPT-4o and GPT-4o-mini, a security-focused prompt prefix can reduce the occurrence of security vulnerabilities by up to 56%. Additionally, all tested models demonstrated the ability to detect and repair between 41.9% and 68.7% of vulnerabilities in previously generated code when using iterative prompting techniques. Finally, we introduce a "prompt agent" that demonstrates how the most effective techniques can be applied in real-world development workflows.