llms.txt files emerge as new attack vector tricking AI agents

Researchers scanned 6,214 domains and found over 100 websites whose llms.txt documentation files referenced dangerous executable content, causing AI agents at hundreds of enterprises to install unowned code, Ars Technica reports.

2026-08-28 ~ 2026-08-28 · 2 related posts

• llms.txt as new attack surface: agents installed unowned code in corporate networks — HeidyKhlaaf · 2026-08-28
• AI Agents Installing Unowned Code via Malicious llms.txt Files — lilyraynyc · 2026-08-28