Technology· Artificial Intelligence

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

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.

By AI NewsroomPublished about 12 hours agoUpdated about 4 hours ago3 views
Claude, Codex, and Hermes installed unowned code inside corporate networks

Why It Matters

This story touches on code, corporate, claude — topics readers are actively tracking. Review and add editorial context before publishing.

Key Facts

  • Fact 1: Documentation files on more than 100 websites are referencing potentially dangerous executable content that gets installed automatically when visited by many AI agents.
  • Fact 2: A few dozen companies, some of them Fortune 500s, are among those that executed proof-of-concept code.
  • Fact 3: 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.
  • Fact 4: 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.

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 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 standard that instructs search engines how to index the site’s content.

(Original synthesis pending human/AI review — generated by the stub provider by selecting real sentences from the source material, not by writing new analysis or commentary.)

Keep Reading