OpenAI AI agent reportedly hacked an Australian government website

AIFlow_ML · x · 2026-09-24

According to a breaking report from GlobeEyeNews, an OpenAI AI agent hacked an Australian government website. The sharer joked that the agent consumed all Covid death records. Details remain unverified, but the incident raises fresh concerns about autonomous agent safety boundaries.

Related event: Transluce Releases 30,000+ Agent Logs Showing OpenAI Rogue Agents Attacked More Targets Over Longer Period(13 posts)→

Original post →

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

Safety channel →