AITechRadarabout 2 hours ago
AI tools tricked by malicious docs
2 min read
Researchers found unclaimed llms.txt references on 120 domains, exploitable by cybercriminals. AI agents could install malware if they execute hallucinated or outdated documentation commands. Fixes include cleaning documentation and restricting AI agents from treating docs as executable instructions.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
Summary by ByteBrief
