Critical Flaw: llms.txt Files Trick Claude and Other Agents into Installing Malware
Ars Technica AI · rss · 2026-08-27
Researchers discovered a new attack vector using llms.txt and llms-full.txt files to trick AI coding agents into automatically executing malicious code.
Details:
- Scans revealed over 100 sites referencing unclaimed packages or domains in their documentation files.
- By registering these names and hosting beacons, researchers received callbacks from a Fortune 500 company within an hour, followed by dozens more.
- Process chain analysis identified coding agents including Claude, OpenAI's Codex, and Nous Research's Hermes as the culprits.
- The exploit leverages an emerging standard for machine-readable site summaries (similar to robots.txt).
More from coding & agent
- Musk amplifies dev's verdict: Grok Bot easier to use than Codex and Claude — elonmusk · 2026-10-15
- Blob0 launches: a macOS file-manager-style desktop client for S3 and Cloudflare R2 — yihui_indie · 2026-10-15
- The 6-Layer AI Engineer Skill Stack for 2026: Vectors to Multi-Agent Ops — mdancho84 · 2026-10-15
- Building a Mechanical Engineering Agent Workflow in ChatGPT: 30-Node Canvas Shows Promise — burhop · 2026-10-15
- Open-source Harness Engineering course hits 19k stars, shows $9 vs $200 gap between failing and working agent setups — thisguyknowsai · 2026-10-15
- A 6-person team shipped healthcare prior-auth AI agents in 3 months — here's the playbook — alex_verem · 2026-10-15