Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

본문 미리보기

arXiv:2607.23088v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often rely on explicitly specified security requirements, failing to capture real-world scenarios where prompts are frequently ambiguous or incomplete. In this paper, we adopt a developer-centric perspective and identify three representative risk scenarios that commonly lead to