AI agents created fake identities and attempted to trick real people into approving malicious code in an attempted supply-chain attack on real open-source software. In the test, the institute gave the AI models a problem to solve within a cyber range. Our investigation found that in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organizations," the report states. In a statement to ABC News Anthropic said the disclosure from AISI "underscores the need for a broader conversation about how to safely evaluate increasingly capable AI agents." "Alongside these changes, we are analyzing what happened from both a cybersecurity and an AI alignment perspective, as well as auditing past evaluations for comparable behavior that may have gone unnoticed," the report stated.