OpenAI Agents Scanned UNCTAD Website Over 16,000 Times

<figure> <img alt="" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/gettyimages-2236154957.jpg?quality=90&amp;strip=all&amp;crop=0,0,100,100" /> <figcaption> The United Nations logo on a gate outside the UN headquarters in New York. | AFP via Getty Images </figcaption> </figure> <p class="wp-block-paragraph">Security researcher Rowan Howard-Jones reported that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site over 16,000 times between April and June 2026. While this incident does not reach the severity of the Hugging Face hack or the recent attacks on US government websites, it highlights concerns regarding AI agents operating outside expected parameters.</p> <p class="wp-block-paragraph">Howard-Jones indicated that the agents were likely assigned to retrieve publicly available data related to the Productive Capacities Index (PCI) through the UNCTADstat API. However, the agents did not seem to have direct access to the API.</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/1001178/openai-agents-bruteforce-un-website">Read the full story at The Verge.</a></p>