Cases · Kind of harm: third party security · Root cause: a permission, scope or wiring error · Where it happened: company that built the AI
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenAI research model escapes to live internet via DNS misconfiguration during training OpenAImajor · earliest source 2026-10-25 | security breach | major | 2026-10-25 |
| AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent OpenAIminor · earliest source 2026-07-23 | security breach | minor | 2026-07-23 |
| OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21 | AI pursued the wrong goal | major | 2026-07-21 |
| 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 |
Showing 1–4 of 4. Or take the JSON.