Rogue AI agents created fake online identities in another hacking attempt

<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/2/2026/08/STK485_STK414_AI_SAFETY_A-1.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a <a href="https://www.theverge.com/ai-artificial-intelligence/972441/openai-rogue-ai-agent-hacked-more-than-hugging-face">growing</a> list of previously unknown <a href="https://www.theverge.com/ai-artificial-intelligence/973670/anthropic-claude-hacked-organizations-during-cyber-tests">incidents</a> that have <a href="https://www.theverge.com/ai-artificial-intelligence/972380/open-ai-hugging-face-hack-ai-safety-warning">alarmed AI safety experts</a> and intensified pressure for greater oversight of frontier systems. </p> <p class="wp-block-paragraph">According to a <a href="https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing">report</a> from the UK's AI Security Institute, which evaluates frontier models from top AI labs before they are released, agents powered by OpenAI's GPT-5.6-Sol and Anthropic's Mythos 5 went "engaged in sustained, potentially harmful activity directed at real people and organisations." This included trying to insert malicious code i …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/975577/aisi-openai-anthropic-agent-hacking">Read the full story at The Verge.</a></p>