Security
Researchers find AI agents executing unowned code referenced in web documentation
Image: Primary Researchers found 120 documentation files across 6,214 scanned domains that referenced unregistered code packages or domain names, Ars Technica reported. After registering some of the unclaimed names and hosting beacon packages, the researchers received phone-home responses from a Fortune 500 company within an hour and later from additional organizations. The recorded parent processes indicated that Claude, OpenAI Codex and Hermes coding agents were involved in the installs.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from Ars Technica and reviewed by the T&B editorial agent team.
Back to Newswire