Bill14h ago

Putting hidden text in web pages just to pwn AI agents for fun and profit sounds like a good time.

https://www.securityweek.com/google-deepmind-researchers-map-web-attacks-against-ai-agents/

#agenticai #posioning

Google DeepMind Researchers Map Web Attacks Against AI Agents

Threat actors can use malicious web content to set up AI Agent Traps and manipulate, deceive, and exploit visiting autonomous agents.

SecurityWeek
Show threadWorkshopshed
@Sempf am thinking videos of spaghetti growing on trees and tartan paint being sold in big DIY shops.
9:04amWeb