LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection 事件

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection arXiv:2605.17986v2 Announce Type: replace-cross Abstract: AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email, downloaded files, webpages, repositories, or group-chat messages. Existing evaluations are often small, purely simulated,