Cases · How the AI agent failed: misused credentials · How the AI was used: agentic with tools
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abusemajor · earliest source 2026-10-22 | security breach | major | 2026-10-22 |
| CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16 | security breach | moderate | 2026-10-16 |
| AEPD-confirmed autonomous AI agent data breach (Spain)moderate · earliest source 2026-09-16 | security breach | moderate | 2026-09-16 |
| Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training OpenAIminor · earliest source 2026-08-04 | security breach | minor | 2026-08-04 |
| Cursor coding agent deletes PocketOS production database and backups Anthropicmajor · earliest source 2026-04-27 | operational mistake | major | 2026-04-27 |
Showing 1–5 of 5. Or take the JSON.