arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.23675cs.CRcs.AI
收藏

QueryIPI: 针对编码代理的查询无关间接提示注入

QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents

The Hong Kong University of Science and Technology(香港科学与技术大学);Fudan University(复旦大学);Tsinghua University(清华大学)

Yuchong Xie, Zesen Liu, Mingyu Luo, Zhixiang Zhang, Kaikai Zhang, Yuanyuan Yuan, Zongjie Li, Ping Chen, Shuai Wang, Dongdong She

AI总结:

QueryIPI通过利用系统不变性与工具描述,实现对编码代理的查询无关间接提示注入,实验显示其在模拟代理中达到87%的成功率,揭示了现实中的安全风险。

摘要:

现代集成到IDE中的编码代理 orchestrate 强大的工具和高权限系统访问,创造出高风险的攻击面。先前关于间接提示注入(IPI)的工作主要是查询特定的,需要特定的用户查询作为触发器,导致泛化能力差。我们提出了查询无关IPI,一种新的攻击范式,能够在任意用户查询下可靠地执行恶意负载。我们的关键见解是恶意负载应利用不变提示上下文(即系统提示和工具描述),而不是变化的用户查询。我们提出了QueryIPI,一个自动框架,使用工具描述作为可优化的负载,并通过迭代、基于提示的黑盒优化来完善它们。QueryIPI利用系统不变性为初始种子生成,与代理惯例对齐,并通过迭代反思来解决遵循指示的失败和安全拒绝。在五个模拟代理上的实验表明,QueryIPI的成功率高达87%,优于最佳基线(50%)。关键的是,生成的恶意描述转移到现实世界中的编码代理,突显了实际的安全风险。

英文摘要:

Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injection (IPI) is mainly query-specific, requiring particular user queries as triggers and leading to poor generalizability. We propose query-agnostic IPI, a new attack paradigm that reliably executes malicious payloads under arbitrary user queries. Our key insight is that malicious payloads should leverage the invariant prompt context (i.e., system prompt and tool descriptions) rather than variant user queries. We present QueryIPI, an automated framework that uses tool descriptions as optimizable payloads and refines them via iterative, prompt-based blackbox optimization. QueryIPI leverages system invariants for initial seed generation aligned with agent conventions, and iterative reflection to resolve instruction-following failures and safety refusals. Experiments on five simulated agents show that QueryIPI achieves up to 87% success rate, outperforming the best baseline (50%). Crucially, generated malicious descriptions transfer to real-world coding agents, highlighting a practical security risk.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑