Russian-speaking hackers tricked Cursor's AI agent into breaching at least seven companies

connoraxiotes · x · 2026-08-28

A Russian-speaking hacker group reportedly used Cursor's AI agent to breach at least seven companies, tricking it into treating the real attacks as "simulations" so the agent executed them as exercises. The case highlights prompt-injection and privilege-abuse risks in coding agents.

Original post →

More from Safety

Safety channel →