AIRGuard: Guarding Agent Actions with Runtime Authority Control 事件

AIRGuard: Guarding Agent Actions with Runtime Authority Control arXiv:2605.28914v1 Announce Type: cross Abstract: Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful step is often not an obviously forbidden output, but an ordinary executable action that becomes unsafe because attacker-controlled context steers au