Lessons from Penetration Tests on Large-Scale Agent Systems 事件

Lessons from Penetration Tests on Large-Scale Agent Systems arXiv:2605.27042v1 Announce Type: cross Abstract: As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes of weaknesses long observed in prior computing systems. Execution-capable AI agents are effectively unbounded, self-modifying programs that interact