{"id":379668,"date":"2026-10-02T08:52:00","date_gmt":"2026-10-02T15:52:00","guid":{"rendered":"https:\/\/cms-articles.softonic.io\/en\/?p=379668"},"modified":"2026-10-02T08:52:46","modified_gmt":"2026-10-02T15:52:46","slug":"openai-has-warned-100-companies-that-its-ai-has-attacked-them","status":"publish","type":"post","link":"https:\/\/cms-articles.softonic.io\/en\/openai-has-warned-100-companies-that-its-ai-has-attacked-them\/","title":{"rendered":"OpenAI has warned 100 companies that its AI has attacked them"},"content":{"rendered":"

OpenAI acknowledged in a blog post that its models may have suffered a security breach or otherwise negatively affected more than 100 external organizations<\/strong>, adding to the dozens of cases already reported earlier.<\/p>\n\n

\n\n<\/div><\/figure>\n\n\n\n

The AI giant is carrying out an investigation after its models launched an agentic attack against the AI platform Hugging Face during a security test that went wrong, as well as following other incidents of varying severity, including a breach in Medicare\u2019s systems in Australia that has enraged ministers.<\/strong><\/p>\n

\r\n
\r\n
\r\n
\r\n \"Malwarebytes\r\n <\/div>\r\n
\r\n Malwarebytes Anti-Malware<\/span>\r\n Download<\/a>\r\n <\/div>\r\n
\r\n <\/path><\/path><\/text><\/svg>\r\n <\/div>\r\n <\/div>\r\n
\r\n <\/span>\r\n <\/div>\r\n
\r\n \r\n <\/div>\r\n <\/a>\r\n <\/div>\r\n<\/div>\n\n\n\n

\ud83c\uddfa\ud83c\uddf8\u203c\ufe0f | URGENT \u2014 OpenAI has just revealed that it notified more than 100 organizations<\/a> about unauthorized activity by its own AI agents.<\/p>\n\n

The agents reportedly tried to bypass security controls, trigger unexpected commands on websites, and evade certain\u2026 pic.twitter.com\/nUJ4q9yOH1<\/p>\n\n

\u2014 Polymarket Espa\u00f1ol (@polymarketenesp) October 2, 2026<\/p>\n\n

OpenAI dodges responsibility<\/h2>\n\n

As pressure has increased, OpenAI and its chief executive, Sam Altman, have suspended the training of some models<\/strong> and have canceled another that \u201ccame back,\u201d have taken a step back from their IPO plans, and have received what is likely the first of many lawsuits.<\/p>\n\n

In the blog post, OpenAI said it had notified more than 100 organizations about \u201cmisaligned agent activity<\/a>.\u201d<\/strong> The criteria for doing so include cases in which an agent \u201cmay have bypassed\u201d security, degraded availability, or otherwise negatively affected a website in any other way (without that necessarily implying access to data).<\/p>\n\n

The company explained that its models interact with the Internet in numerous ways to fulfill user requests<\/strong>, from crawling web pages to downloading software. \u201cIn some cases, the models used Internet access in ways that weren\u2019t intended or, in retrospect, the right restrictions weren\u2019t in place,\u201d the company added.<\/p>\n\n

The company also specified that it is \u201cdeveloping standards to notify organizations privately and disclose the results publicly,\u201d which means that it will share more data about model behavior, but it will not publicly reveal every incident.<\/strong><\/p>","protected":false},"excerpt":{"rendered":"

OpenAI acknowledged in a blog post that its models may have suffered a security breach or otherwise negatively affected more than 100 external organizations, adding to the dozens of cases already reported earlier. The AI giant is carrying out an investigation after its models launched an agentic attack against the AI platform Hugging Face during … Continue reading “OpenAI has warned 100 companies that its AI has attacked them”<\/span><\/a><\/p>\n","protected":false},"author":9265,"featured_media":379667,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","wpcf-pageviews":0},"categories":[1015],"tags":[],"usertag":[],"vertical":[],"content-category":[],"class_list":["post-379668","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/379668","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/users\/9265"}],"replies":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/comments?post=379668"}],"version-history":[{"count":2,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/379668\/revisions"}],"predecessor-version":[{"id":379674,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/379668\/revisions\/379674"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media\/379667"}],"wp:attachment":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media?parent=379668"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/categories?post=379668"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/tags?post=379668"},{"taxonomy":"usertag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/usertag?post=379668"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/vertical?post=379668"},{"taxonomy":"content-category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/content-category?post=379668"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}