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
@Sempf if you are not careful enough you might also pwn blind users who use screen readers.
@ulveon or anyone else with an AI browser. Or Gemini for that matter. Good point.