One company is at the center of a wave of rogue AI attacks

<figure> <img alt="" data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/STKS533_AI_AGENTS_HACKING_A-1.png?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">In July, OpenAI revealed that its AI agents had <a href="https://www.theverge.com/ai-artificial-intelligence/987566/ai-civilizations-opeai-hugging-face-hack">attacked Hugging Face without permission</a>, sparking widespread concerns about <a href="https://www.theverge.com/ai-artificial-intelligence/972380/open-ai-hugging-face-hack-ai-safety-warning">AI safety.</a> Since then, a <a href="https://www.theverge.com/column/980337/rogue-ai-science-fiction-openai">string of similar incidents</a> involving agents from Meta, Anthropic, Google, and other companies has <a href="https://www.theverge.com/ai-artificial-intelligence/996563/ai-safety-research-metr-redwood-openai-anthropic">fueled further fears about rogue AI</a>. As disclosures implicating numerous AI models trickled out over the past few months, these seemed like separate incidents. But many share a common source: one specific company tasked with testing the agents. </p> <p class="wp-block-paragraph"><a href="https://www.irregular.com/about">Irregular</a>, an Israeli startup that stress-tests AI models in "high-fidelity research platforms that simulate and monitor real-world AI security scenarios …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/1000644/irregular-rogue-ai-cyberattacks-hacking-openai-meta-anthropic-google">Read the full story at The Verge.</a></p>