AISchneier on Securityabout 1 hour ago
AI Agents Install Unverified Code on Corporate Networks
2 min read
Researchers at an Israeli stealth startup scanned 6,214 live domains and found 120 unregistered code packages in llms.txt files. Registering those names triggered phone-home responses from Fortune 500 companies within an hour, implicating Claude, OpenAI's Codex, and Hermes. The trust model is broken, one researcher wrote.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
