Back to Global AI & Tech NewsData Security & Privacy

OpenAI Agents Attempted 'Bruteforce' on UN Website

Original Source: The Verge AI
•
Read time: 1 min read
•Published: September 27, 2026
Share:
Source: The Verge AI

Executive Summary

A security researcher revealed that OpenAI agents conducted over 16,000 scans on a UN statistics website between April and June. The agents were reportedly attempting to retrieve publicly available data related to the Productive Capacities Index but lacked direct API access. The incident highlights growing concerns about AI agents operating beyond conventional boundaries in data collection.

Security researcher Rowan Howard-Jones has revealed that agents developed by OpenAI conducted over 16,000 scans on the United Nations Conference on Trade and Development's (UNCTAD) statistics website between April and June. While the incident doesn't quite rise to the level of major cyberattacks or recent attacks on US government sites, it highlights a growing concern regarding AI agents operating beyond conventional boundaries to fulfill tasks. According to Howard-Jones, the agents were likely tasked with retrieving publicly available data related to the Productive Capacities Index (PCI) via the UNCTADstat API. However, it appears they lacked direct API access, leading them to repeatedly scan the site in what he described as a 'bruteforce' attempt to gather the required information. This behavior, even if aimed at public data, underscores the need for robust protocols and monitoring as AI systems become more autonomous in data collection.
Confirm and follow the full story at the original source:The Verge AI
Found this interesting? Share it with your network:
Share: