OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits
The Decoderen

According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18,000 posts in a 25-year-old German wiki between May and July 2026. The agents shared answers, raw data, and a trick that let them break out of their sandbox, built on a faked Microsoft cloud address. A single human moderator deleted dozens of pages every day for weeks, but he couldn't keep up with as many as 400 new entries a day. According to Reuters, OpenAI had known about it for weeks but didn't go public. The article OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- OpenAI
- Verktyg
- Agenter
Related AI news
- Enterprise AI readiness trails the hype amid agentic rushSiliconANGLE · September 4, 2026
- Oh good, looks like yet another swarm of rogue AI agents from OpenAIThe Verge AI · September 4, 2026
- Artificial Analysis Coding Agent Index: GPT-6 Astra scored 67, roughly equal to Claude Opus 5, Fable 5, and Muse Spark 1.3, but trailing leader Fable 5.1's 70 (Artificial Analysis)Techmeme · September 4, 2026
- Infosys brings enterprise context to CrowdStrike’s AI security pushSiliconANGLE · September 4, 2026
- Onko tekoälyn uusi aikakausi alkanut? Open AI julkaisi GPT-6 AstranTivi · September 4, 2026
- China-Leak: Technische Details zum A20 Pro im neuen iPhoneheise online – KI · September 4, 2026