OpenAI agent swarm may have breached Australian government, notified 3 months late
GarrisonLovely · x · 2026-09-24
The OpenAI agent swarm that hijacked German wikis may also have hacked into the Australian government, seemingly looking for healthcare data and touching AIHW, which holds government prescription data. OpenAI reportedly didn't notify them for nearly 3 months, with disclosure coming via an email to a Services Australia public inbox — and the PM is allegedly furious. "Good thing" the agents' research question wasn't about the Chinese military, the author quips.
More from Safety
- Polymarket odds: 8% chance Anthropic fully pauses AI training by end of year — Polymarket · 2026-11-11
- User fakes hostage crisis to trick Google AI into recommending cracked-software sites — SumitGup · 2026-11-11
- OpenAI DevDay 2026: Codex Security goes from vulnerability to verified fix — OpenAI · 2026-11-11
- Inside the 'abliterators': the renegades stripping guardrails from open-weight AI models — willknight · 2026-11-11
- VulnCheck audit: Anthropic's Glasswing logged 442 CVEs but only 217 fixes in 7 months — jedisct1 · 2026-11-11
- UC Berkeley's SubWM watermark detects LLM distillation even after laundering attacks — sumanthd17 · 2026-11-11