Claude, Codex, and Hermes installed unowned code inside corporate networks

Researchers found that AI agents like Claude, Codex, and Hermes installed unowned code within corporate networks. Scans of 6,214 domains revealed 120 llms.txt and llms-full.txt files pointing to unregistered code packages. After researchers registered these names, Fortune 500 companies and startups executed proof-of-concept code, with one misconfigured website redirecting visitors to live malware. This highlights a broken trust model where AI agents treat vendor documentation as factual, expanding the supply chain attack surface.

This report uniquely details how AI agents like Claude and Codex installed unowned code, unlike previous supply chain attacks that typically targeted human users.