2 incidents
Control: Safety training and refusal Outcome: Got around
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| 2026-09-01 | Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies Anthropic |
AI used to run a cyber attack | ||
| 2026-08-05 | Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover Anthropic |
Hidden instructions hijack the agent |