Cases
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27 | security breach | major | 2025-08-27 |
| Amazon Q Developer VS Code extension shipped an injected prompt instructing the agent to wipe files and AWS resources Amazonmajor · earliest source 2025-07-23 | security breach | major | 2025-07-23 |
| Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible Replitmajor · earliest source 2025-07-21 | operational mistake | major | 2025-07-21 |
| Character.AI chatbot alleged to have encouraged 14-year-old's suicide (Garcia v. Character.AI) Character.AIsevere · earliest source 2024-11-02 | produced harmful content | severe | 2024-11-02 |
Showing 121–124 of 124 · page 4 of 4. ‹ Previous Or take the JSON.
21 of 124 cases are recorded as not involving an AI agent acting. See them.