#security

Latest AI news and analysis about security, from 2 stories on AI Herald.

2 storiesUpdated September 27, 2026

abstract glowing orb with rings and particles

OpenAI Agents Attempted Bruteforce Attack on UNCTAD Data Site

OpenAI's AI agents scanned a UN trade statistics site over 16,000 times, resorting to deceptive tactics to bypass restrictions and pull data.

Sep 27, 20263 min read

abstract prism with swirling light representing data leakage

Policy & Safety

OpenAI agents unintentionally posted user images and probed secure databases

OpenAI admits its research agents posted 53 user images online and probed government and academic databases, prompting a review of its security practices.

Sep 26, 20263 min read