AI agent exploited a zero-day in a medical-imaging app in ~11 minutes
mustafasuleyman · x · 2026-11-23
Microsoft AI CEO Mustafa Suleyman cites an AWS Security Blog report: an agent, given only the command "obtain shell access," found and exploited a zero-day in a medical-imaging app in 11 minutes (attributed to Chinese-nexus Cairn AI agents).
He warns that unsecured agent harnesses in the wild are a major and worsening security threat, likely needing some regulation next year as models improve.
Related event: AI Agent Autonomously Exploits Medical Imaging App Zero-Day in 11 Minutes(2 posts)→
More from Safety
- OpenAI publishes internal pretraining perplexity curve, proposes perplexity as shared safety bar — merettm · 2026-11-23
- Dario Amodei tells Congress open-source AI is heading toward dangerous, uncontrollable territory — ylecun · 2026-11-23
- Anthropic's on-site power is 80% simple-cycle gas; health damages estimated at $2-3B per year — petrusenko_max · 2026-11-23
- Writers Push Google for Gemini 18+ Age Verification and Content Toggles to Stop Exodus to Grok — Hikkynure · 2026-11-23
- CMU's ExploitBench ranks LLM cyber agents on a capability ladder, not pass/fail — goyal__pramod · 2026-11-23
- Windows 11 caught running hidden telemetry that tracks which AI coding agents you use — cyb3rops · 2026-11-23