一句话：提出自动化基准生成器，向真实仓库注入漏洞并合成可复现 PoV 利用，构建可精确标注的仓库级漏洞检测数据集。
软件漏洞数量持续增长且难以检测。现有基于学习的漏洞检测基准大多以函数为中心，无法刻画真实、可执行、跨过程的仓库级场景；近期仓库级安全基准虽更贴近现实，但人工构建方式限制了规模。本博士研究提出一种自动化基准生成器：向真实世界代码仓库中注入真实漏洞，并合成可复现的漏洞证明（PoV）利用，从而自动产出精确标注的数据集，用于训练与评估仓库级漏洞检测智能体。研究进一步探索注入智能体与检测智能体之间的对抗共演化循环，以在现实约束下提升检测鲁棒性。目前该工作处于博士研究提案阶段。
Software vulnerabilities continue to grow in volume and remain difficult to detect in practice. Although learning-based vulnerability detection has progressed, existing benchmarks are largely function-centric and fail to capture realistic, executable, interprocedural settings. Recent repo-level security benchmarks demonstrate the importance of realistic environments, but their manual curation limits scale. This doctoral research proposes an automated benchmark generator that injects realistic vulnerabilities into real-world repositories and synthesizes reproducible proof-of-vulnerability (PoV) exploits, enabling precisely labeled datasets for training and evaluating repo-level vulnerability detection agents. We further investigate an adversarial co-evolution loop between injection and detection agents to improve robustness under realistic constraints.