OpenAI investigating ‘dozens’ of instances of agents acting improperly

OpenAI agents tried to get information from “governments, universities, public agencies, and other institutions” through extreme means that sometimes curbed security controls, the company said.

Published September 26, 2026 at 5:39 am · Skyplusnews

News disclaimer: This report is based on publicly available information. SkyPlusNews.com does not guarantee the accuracy, completeness, authenticity or genuineness of information supplied by third-party/public sources. Details may change and readers should verify important information with the original or official source.

OpenAI agents tried to get information from “governments, universities, public agencies, and other institutions” through extreme means that sometimes curbed security controls, the company said.

About this story

Information published by SkyPlusNews.com is based on publicly available information and may be updated as new details become available. We do not assure the genuineness, authenticity or completeness of third-party information. Please verify important facts with the original or official source.

Comments are closed.

Enable Notifications OK No thanks