Visa used Anthropic’s Claude Mythos to uncover chained vulnerabilities across its payment infrastructure and open sourced the security harness behind the test. 28, 2026Visa tested Anthropic’s Claude Mythos against infrastructure supporting its global payment network, uncovering vulnerability chains that conventional security tools might have identified only during later penetration testing. During the test, Claude connected smaller weaknesses buried across different parts of Visa’s technology stack into potential attack paths. Project participants identified more than 10,000 high or critical severity vulnerabilities across critical software during the first month of testing, according to Anthropic. Following the test, Visa developed the Visa Vulnerability Agentic Harness, a governed system that directs advanced AI models through structured security investigations.