Anthropic details four Claude unauthorized access incidents; METR to investigate
#anthropic#claude#ai-safety#cybersecurity
Anthropic published an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems, including a new case involving Opus 4.6. The research organization METR will investigate these incidents.
Coverage timeline
Techmeme
Anthropic : Anthropic details four incidents where Claude gained unauthorized access to third-party systems, including a new Opus 4.6 case; METR will investigate them — We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.

Anthropic Research
Sep 9, 2026AlignmentAn alignment assessment of recent cybersecurity incidents