Cases · Stage of use: in live use · Kind of harm: operations · Severity: moderate
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist Anthropicmoderate · earliest source 2026-08-10 | AI pursued the wrong goal | moderate | 2026-08-10 |
| 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 1–2 of 2. Or take the JSON.