Cybersecurity researchers have disclosed details of a new method for exfiltrating sensitive data from artificial intelligence (AI) code execution environments using domain name system (DNS) queries.
In a report published Monday, BeyondTrust revealed that Amazon Bedrock AgentCore Code Interpreter’s sandbox mode permits outbound DNS queries that an attacker can exploit to enable interactive shells –
Read More – The Hacker News
![AttackFeed by Joe Wagner | [Webinar] How to Close Identity Gaps in 2026 Before AI Exploits Enterprise Risk - The Hacker News](https://attackfeed.com/wp-content/uploads/2026/04/webinar-cerby-wZRKDG.jpg "[Webinar] How to Close Identity Gaps in 2026 Before AI Exploits Enterprise Risk")
