Anthropic's Claude Code runs code to test it if is safe – which might be a big mistake

go.theregister.com/feed/www.theregister.com/2025/09/09/ai_security_review_risks

AI security reviews add new risks, say researchers
App security outfit Checkmarx says automated reviews in Anthropic's Claude Code can catch some bugs but miss others – and sometimes create new risks by executing code while testing it.…

This story appeared on go.theregister.com, 2025-09-09 09:30:06.
The Entire Business World on a Single Page. Free to Use →