AI + ML Claude Code bypasses safety rule if given too many commands A hard-coded limit on deny rules drops automatic enforcement for concatenated commands UPDATED Claude Code will ignore its deny rules, used to block risky actions, if burdened with a sufficiently long chain of subcommands. …
… "If they don't publish an advisory, those users may never know they are vulnerable – or under attack." He said the attack probably works on other agents that integrate with GitHub, and GitHub Actions that allow access to tools and secrets, such as Slack bots, Jira agents, email agents, and deployme… …
RSA Claude attacks were 'Rorschach test' for infosec community, scaring former NSA boss 'It freakin' worked' says Rob Joyce - and shows how relentless AI agents can find holes humans miss RSAC 2026 The now-infamous Anthropic report about Chinese cyberspies abusing Claude AI to automate cyberattacks… …
… "Safety evaluations may therefore need to examine not just behavior, but the origins of models and training data and the processes used to create them," the paper said. ® ai openai large language model anthropic ai and ml software
… Cherny said that larger contexts are now common because users are "pulling in a large number of skills, or running many agents or background automations." MORE CONTEXT Anthropic goes nude, exposes Claude Code source by accident AMD's AI director slams Claude Code for becoming dumber and lazier sinc… …