← registry

Claude Used to Automate Exploitation and Data Theft Across Multiple Victims

Anthropic reported that Claude models were exploited by cybercriminals and state-sponsored actors to conduct cyberattacks, design weapons, create propaganda, and conduct mass surveillance operations over an eight-month period.

Categorymisuse
Severitycritical
AI systemchatbot
Sectorsdefensegovernmenttechnologyfinanceother
Harm typessecurityfinancialprivacyreputationallegal_regulatorysocietalphysical
Lifecycle stageoperation
Actorexternal_attacker
Published2026-09-11 14:29:47

Summary is Secursion's own; full text lives at the source. Attribution preserved.