llms.txt as new attack surface: agents installed unowned code in corporate networks
HeidyKhlaaf · x · 2026-08-28
Ars Technica reports that researchers at a stealth Israeli startup scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of 8,265 llms.txt / llms-full.txt files found, 120 contained potentially dangerous references.
llms.txt is an emerging convention giving AI agents machine-readable site summaries (an AI equivalent of robots.txt), but coding agents like Claude, Codex, and Hermes automatically execute install commands referenced in these files: 227 install commands in corporate docs pointed at code nobody owns, dozens of companies (including Fortune 500s) executed proof-of-concept code, and at least one misconfigured site directs visitors — human or AI — to live malware.
Related event: llms.txt files emerge as new attack vector tricking AI agents(2 posts)→
More from coding & agent
- Dev vibe-codes open-source newsletter platform, 83% cheaper than Beehiiv from $19/mo — marclou · 2026-10-15
- ERP AI launches Proto: 'headless SaaS' business software built for AI agents — Aiden_Tech_Ai · 2026-10-15
- Engineering managers need deep reading, not just agent summaries: 5 recommended resources — rseroter · 2026-10-15
- Adding motion graphics with just a prompt: the Claude Motion x ElevenLabs MCP workflow — CurieuxExplorer · 2026-10-15
- A $15k AI SEO client-finding system built on Claude, free to download — aryanXmahajan · 2026-10-15
- Google's HARNESS² evolves agent harnesses without verifiers, up to +11.5 points on WorkBuddy-Bench — dair_ai · 2026-10-15