Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation

Abstract

Large Language Models have become powerful tools for programming. However, they often overlook essential security practices, producing code with vulnerabilities. Despite this risk, existing work offers limited guidance on steering LLMs toward secure code generation and lacks systematic analysis of how effectively LLMs repair vulnerable code. In this work, we investigate how LLMs can be guided to prevent and repair code vulnerabilities. Specifically, we examine whether self-generated vulnerability hints help models avoid insecure code, and evaluate how different feedback levels influence vulnerability repair . Our study considers proprietary and open-weight models across multiple scales and uses established benchmarks covering diverse vulnerability types. Our results show that self-generated vulnerability hints meaningfully reduce insecure code, with effectiveness depending strongly on relevance and preciseness. We further find that more directive hints, which explain how it could arise in the task and specify how to avoid it, more effectively prevent vulnerable code. For post-hoc vulnerability repair, raw detection-tool feedback improves security across all models, while detailed, actionable explanations provide further gains on two of the three benchmarks, especially for models with stronger instruction-following capabilities. Yet, this explained feedback does not consistently outperform the raw feedback for the benchmark containing real-world tasks triggering multiple weaknesses.