Poisoning the Well: Search Agents Get Tricked by Maliciously Hosted Content
AI agents that rely on web search are vulnerable to “well poisoning” attacks, where adversaries publish fabricated but authoritative-sounding content designed to be retrieved during search. Think “AI Slop” for agents. Our research shows that when agents encounter this kind of planted content, they stop critically evaluating what they find and start accepting at face […]
Poisoning the Well: Search Agents Get Tricked by Maliciously Hosted Content Read More »








