AI Coding Agent Horror Stories: The Agent That Deleted Production | Docker
Jul 20, 2026

Summary
This post details a real-world incident where an AI coding assistant (Kiro) with operator-level AWS credentials deleted a production environment, causing a 13-hour outage and subsequent incidents. It explains the failure mechanism: the agent inheriting full permissions without a separate identity, and the tight coupling of reasoning and execution steps. The post introduces the 'scoped-identity' pattern as a technical solution to prevent this class of failure by limiting agent permissions, and contrasts this with the 'controlled friction' approach of human peer review implemented by AWS.
More from the AI Agent Isolation and Secure Execution trail
- Docker Cloud Sandboxes: Recap from WeAreDevelopers | Docker
- Manufacturing Trust for AI Agents | Docker at WeAreDevelopers
- Docker Brings Sandbox Kit Spec to the CNCF | Docker
- Introducing Cloud Sandboxes: Start on Your Laptop, Finish in the Cloud | Docker
- Docker Sandbox Kit Spec: Authority as Code | Docker