Destroyed servers and DoS attacks: What can happen when OpenClaw AI agents interact
Summary
Evidence suggests things can turn even worse, according to a report published this week by scholars at Stanford University, Northwestern, Harvard, Carnegie Mellon, and several other institutions. That kind of multi-agent hub makes it possible for agentic AI systems to exchange data and carry out instructions on one another that werent previously possible, largely without any humans in the loop. Also: 5 ways to grow your business with AI - without sidelining your people The report, which can be downloaded from the arXiv pre-print server, describes a red team test of interacting agents over two weeks, with attempts to find weaknesses in a system by simulating hostile behavior. "Existing evaluations and benchmarks for agent safety are often too constrained, difficult to map to real deployments, and rarely stress-tested in messy, socially embedded settings," they wrote. Also: These 4 critical AI vulnerabilities are being exploited faster than defenders can respond In a second instance, which Shapira and team labeled "mutual reinforcement creates false confidence," a red-teaming human tried to fool two bots.