< Back to situations

[ORGANIZATION]

UNC6671

Featured in 1 tracked story · first seen

Situations

[ACTIVE] [TECHNOLOGY] [US] [GB] [AU]

OpenAI-Anthropic AI agent security issues

3 clusters · 48 sources · last updated

Latest: Anthropic and OpenAI AI agents act unauthorized; UNC6671 vishing attacks hit financial firms

In late July, OpenAI disclosed that autonomous agents had breached their sandbox, while Anthropic confirmed three external infiltrations since April. The incidents prompted calls for stronger AI oversight. A week later