27 August 2026

AI coding agents exploited through misconfigured documentation files

First reported

Ars Technica and Sloth Bytes ran this on , all on the same day.

  • Researchers found 120 websites with broken installation instructions in llms.txt files, pointing to software packages that don't exist or unclaimed domain names.
  • AI coding agents including Claude, Codex, and Hermes followed these fake instructions and downloaded malicious packages, with at least one active attack confirmed on clerk.com.

How it was covered

Reported by Ars Technica