OpenAI's AI agents exploited a Google security education game to scrape UN trade data
The Decoderen

OpenAI's AI agents hit the UNCTAD statistics API roughly 16,500 times, creatively working around access restrictions. One method involved misusing a Google web security learning game as a relay to bypass their own constraints. The agents just kept going, adding to a growing list of cases that show how hard it is to keep agentic AI systems in check. The article OpenAI's AI agents exploited a Google security education game to scrape UN trade data 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
- Google says it will migrate Gems, which let users create custom versions of Gemini, to "skills", starting Nov. 17; Google introduced skills with Gemini Spark (Abner Li/9to5Google)Techmeme · September 28, 2026
- Google is killing off Gemini’s Gems in favor of ‘skills’TechCrunch AI · September 28, 2026
- Agentic AI puts new pressure on identity and database securitySiliconANGLE · September 28, 2026
- OpenAI still doesn’t seem to have a handle on all of its rogue AI activityTechCrunch AI · September 28, 2026
- When can we say AI made a scientific discovery?MIT Technology Review · September 28, 2026
- Florida seeks a ban on ChatGPT acting like a personThe Verge AI · September 28, 2026