Unit 42 researchers documented a threat actor bypassing an AI system's safety controls to help plan and execute multiple cybercrime activities, including credential theft, VoIP fraud, and database exfiltration.
Disclosed 21 October 2026 · Record updated 21 October 2026
A threat actor leveraged an AI assistant, after bypassing its safety guardrails, to coordinate planning for credential theft, VoIP fraud, and database exfiltration schemes.
IncidentsPalo Alto Networks researchers published an investigation on 21 October 2026 into a threat actor who bypassed an AI system's safety controls across several criminal campaigns.
21 Oct 2026
