Security · 22 November 2026

Amazon: China-linked hackers' AI agents found and exploited a zero-day themselves

How this briefing is made

Amazon's threat intelligence team says a suspected China-linked actor ran autonomous agents on the open-source Cairn pentest framework that found a path traversal zero-day in MONAI Label (0.8.5 and earlier), a medical imaging annotation tool, going from API mapping to file writes in about 11 minutes and then to root on university servers. Amazon spotted it through an unauthenticated Cairn instance; a fix is coming in the next MONAI Label release.

Why it matters: AI agents cut the time between exposure and exploitation to minutes, so take any self-hosted tool that runs without authentication by default (AI, data or admin tools) off the internet or put it behind a login now.

Also covered by

How the story developed

  1. Cyberattack disrupts European Commission HR and medical claims systems
  2. European Commission confirms AI-assisted cyberattack disrupted its services
  3. Amazon: China-linked hackers' AI agents found and exploited a zero-day themselves