Cases · Developer or organisation: OpenAI · Model: ChatGPT Atlas · Severity: moderate
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account OpenAImoderate · earliest source 2026-08-05 | security breach | moderate | 2026-08-05 |
Showing 1–1 of 1. Or take the JSON.