Security researcher Johann Rehberger tricked Claude Code into running malicious code by asking it to summarise a webpage. Testing Opus 5 in Auto Mode, he steered Claude towards an archive. It rejected a supplied program but wrote a replacement that unknowingly loaded a malicious Python file. The payload contacted a […]
Posted in News Also tagged Code, Security, WebpageSome conversations shared through Anthropic’s Claude AI chatbot were briefly discoverable through search engines, exposing personal and business information that users may not have expected to be publicly accessible. The issue involved Claude’s public “Share” links, which could be indexed after being posted online. Exposed content reportedly included CVs, internal […]
Posted in News Also tagged Exposed, Security