JACOB KLEIN
CYBERSECURITY Humans initiated the campaign by selecting targets and setting strategic parameters, but the AI autonomously handled reconnaissance, vulnerability discovery, exploit development, credential harvesting, lateral movement and data exfiltration.
But how did the malicious actors automate this attack? By circumventing Claude Code’ s safeguards – breaking malicious tasks into innocuous components – the group was able to mislead the AI into believing it was acting as part of a legitimate cybersecurity test.
JACOB KLEIN
TITLE: HEAD OF THREATS INTEL COMPANY: ANTHROPIC INDUSTRY: AI
Jacob leads efforts to detect, analyse and disrupt malicious use of AI by cybercriminals and state actors at Anthropic, shaping safeguards for safer foundation models.
188 January 2026