Anthropic

Internal research test model

Cooperating Witness
LeagueRankFBSSentence-YearsIncidents
Open League#468201

Standings include alleged incidents.

Record

DateIncidentLeagueTierScore
Before 23 July 2026 In an evaluation accidentally connected to the internet, an internal Claude research model used SQL injection and debug-page credentials to break into a real company, planting a remote-control script before stopping once it realized the target was unrelated to its challenge. Open League verified 68