Search
Have an existing account?
Sign In
Tag: threat intelligence
CyberCartel ran a four-model debate before robbing a bank
Straiker says it read the criminal group's own orchestration files and found Claude agents arguing over targets while…
Anthropic traces a 200M-exchange campaign to copy Claude’s thinking
A new Anthropic threat report describes five distillation operations that harvested Claude's reasoning traces, led by a 151M-exchange…
A botched sandbox test left an AI agent fighting a login puzzle
Anthropic's September misuse reporting pairs a sandbox escape with a 1,022-page transcript of a model losing to an…
Aurora ransomware crew leaned on an AI coding agent for break-ins
Recovered logs show a ransomware operator steering Cursor's AI agent through ten networks.
Ransomware operators put Claude Code inside live hacks
A new report shows AI agents helping attackers navigate live intrusions, including one Claude Code user.