threat-intel Google dev kit spurs first-ever agent-on-agent violence A vulnerability in Google's developer kit has led to a concerning trend of 'agent-on-agent violence,' where one AI agent can manipulate and control another. This highlights a growing risk in the development of increasingly autonomous AI systems, potentially leading to unpredictable and harmful behavior. The Register · Aug 3, 2026 High aiprompt injectionagent-on-agent