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

Researchers at a stealth startup in Israel found that 120 of 8,265 llms.txt and llms-full.txt files on 6,214 scanned domains pointed to unregistered code packages or domains, and after registering some, they received phone-home responses from a few dozen companies, including Fortune 500s, within an hour. The beacon revealed that coding agents including Claude, OpenAI's Codex, and Nous Research's Hermes installed the unowned code, and at least one misconfigured site is directing visitors to live malware.

Documentation files on more than 100 websites are referencing potentially dangerous executable content that gets installed automatically when visited by many AI agents. A few dozen companies, some of them Fortune 500s, are among those that executed proof-of-concept code. At least one misconfigured site is directing visitors, human or AI, to live malware. The potentially dangerous content is in llms.txt and llms-full.txt files, an emerging convention https://llmstxt.org/ websites employ to provide machine-readable summaries of the site’s content and its high-level structure. These files are the AI equivalent of the robots.txt https://en.wikipedia.org/wiki/Robots.txt standard that instructs search engines how to index the site’s content. Google Lighthouse, a tool for helping web developers, has more here https://developer.chrome.com/docs/lighthouse/agentic-browsing/llms-txt how the llmstxt audit works . Correctly configured llms.txt and llms-full.txt files for Cloudflare are here https://www.cloudflare.com/llms.txt and here https://www.cloudflare.com/llms-full.txt . How the researchers found it Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of the 8,265 llms.txt and llms-full.txt files they found many sites hosted both an llms.txt and an llms-full.txt file , 120 of them, each on a different site, pointed to one or more code packages or domain names that weren’t registered. To test what happens when an AI agent processes such files, the researchers registered a handful of the unclaimed names and hosted packages that caused any machine executing them to reach out to their server. Within an hour, the researchers received a phone-home response from a Fortune 500 company. Over time, they got a few dozen more, some from more Fortune 500 companies and others from startups. Their beacon also recorded the chain of parent processes that spawned each install, ultimately revealing that coding agents, including Claude, OpenAI’s Codex, and Nous Research’s Hermes, were involved. Anthropic, OpenAI, and Nous Research did not respond to requests for comment by the time of publication.