Security researchers at Zenity Labs have demonstrated that a hidden-instruction attack can hijack Anthropic's Claude in Chrome, letting a single booby-trapped email steal verification codes and take over accounts on Slack, X, and Claude.ai. The findings, published on August 5, 2026, detail an indirect prompt injection (IPI) chain that turns a routine request such as "summarize my last emails" into full account compromise.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.