Originally published byThe Hacker News
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
🇺🇸
More news from United StatesUnited States
NORTH AMERICA
Related News
Open Harness: The Multi-Panel AI Powerhouse Revolutionizing Developer Workflows
5h ago
Firefox Announces Built-In VPN and Other New Features - and Introduces Its New Mascot
4h ago
CBS News Shutters Radio Service After Nearly a Century
4h ago
50% of Consumers Prefer Brands That Avoid GenAI Content
4h ago
Officer Leaks Location of French Aircraft Carrier With Strava Run
4h ago