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.
More from Safety
- Incoming Berkeley prof: AI firms spend billions on alignment, orders of magnitude less on agent control — sayashk · 2026-08-28
- Proposal to limit single training run compute increase for safety — louisvarge · 2026-08-28
- Proposal for incredibly incremental AI release cadence via compute limits — louisvarge · 2026-08-28
- Safety measures for OpenAI apps if the platform is hacked — Astrokanu · 2026-08-28
- WSJ op-ed editor says no need to disclose AI writing; author predicts market will decide — TuhinChakr · 2026-08-28
- METR report on Hugging Face attack hailed as first anthropology of posthuman civilization — anderssandberg · 2026-08-28