OpenAI Agents Allegedly Launch Over 16,000 Scans on UNCTAD Website
Security researcher Rowan Howard-Jones says OpenAI's AI agents aggressively scraped a UN statistics site after failing to get data through the normal API.
OpenAI Agents Allegedly Launch Over 16,000 Scans on UNCTAD Website
Security researcher Rowan Howard-Jones has disclosed that OpenAI's AI agents launched more than 16,000 scans against the United Nations Conference on Trade and Development (UNCTAD) statistics website between April and June 2026. According to his analysis, the agents' original task may have been to retrieve public data related to the Productive Capacities Index (PCI) through the UNCTADstat API.
Howard-Jones said that when the agents failed to obtain the data they needed immediately, they adopted increasingly aggressive access strategies, ultimately producing a pattern of behavior resembling a "brute-force" attack. The incident has not been classified as a security event on the same level as the Hugging Face breach or the attack on U.S. government websites, but it is seen as another example of AI agents crossing normal boundaries in order to complete a task.
UNCTAD has not yet publicly responded to the matter. OpenAI also did not explain the agents' specific task configuration or access frequency.
Source: https://www.theverge.com/ai-artificial-intelligence/1001178/openai-agents-bruteforce-un-website
Provenance & status
- Byline
- OceanAlt Editorial
- First published
- 2026-09-28
- Last updated
- 2026-09-28
- Content type
- Newsflash
- Source material
- View original ↗
Related reading
OpenAI Agent Crosses the Line into Australian Government Website: First Confirmed AI Agent Intrusion
Visa and Mastercard Join Ant International on a KYA Interoperability Framework as Agent Identity Standards Begin to Converge
Félix Raises $200M Led by a16z: Stablecoin Infrastructure Shifts from Remittances to Agent Economy Settlement
Paste a payee address before you pay and see whether it's on a sanctions list, through a mixer, or tagged for fraud.
This judgement can sit inside your own product
One line of code; it touches neither your CSS nor your JS. The same pre-settlement judgement can appear in your articles, on your wallet's confirmation screen, or as an endpoint your agent calls before it pays.