Research suggests ChatGPT maker's agents got creative when a UN data API proved less than cooperative.
OpenAI agents spent two months hammering a United Nations data API, trying creative ways to bypass the barriers they encountered.
Researcher Rowan H-J uncovered the activity by analyzing about 16,500 scans of the UN Conference on Trade and Development's UNCTADstat API recorded between April 13 and June 19, 2026.
Rowan claims it’s "highly likely" the traffic came from OpenAI agents, based on links to before documented OpenAI "wiki swarms," overlapping Azure IP addresses, and payloads carrying labels including “CHATGPTTEST1” and “OAI_META_1312.”
OpenAI told The Register it is looking into the findings, though it stopped short of explicitly confirming that its agents were responsible for the activity Rowan documented.
The spokesperson pointed to OpenAI's before announced review of what it calls "misaligned model activity," saying most of the behavior examined so far involved routine research, including accessing public websites to answer questions.
The agents appear to have been hunting for unexciting public data on things like trade, work, and productive capacity.
According to Rowan's analysis, the agents experimented with third-party services that could make requests on their behalf and built bits of JavaScript to fetch the data.
On June 1, one attempt returned nine rows of work data.
Rowan counted the same technique being used 55 times between May 4 and June 19.
Rowan also found that 45 of the 54 Azure IP addresses associated with UNCTAD-related activity on the wikis had before edited DseWiki during the earlier agent group.