Reported by 3 outlets

Timeline

1. update from cyberscoop.com

   Irregular says ‘human oversight’ responsible for AI sandbox escape incidents

   cyberscoop.com · 57d ago · August 17th, 2026

   A company that runs AI testing labs involved in a series of breaches carried out by Anthropic and OpenAI’s cyber-focused models said the incident happened in part because they “unintentionally” provided the models with access to the internet. In a blog posted Friday, Irregular said it partners with frontier labs to “stress test” AI models for security risks before they’re deployed, including simulations of their vulnerability research capabilities. Those tests included non-public models from Anthropic and OpenAI. Separate disclosures from the companies confirmed these included Mythos 5, Claude Opus and GPT-5.6 Sol. “As part of our review, we identified that a few interactions with our evaluation environments, in which internet access was unintentionally made available, led some models to take offensive security actions in the real world,” Irregular said in an unsigned blog. In the incidents involving Anthropic’s models, testers initially believed the models were using a fictional company in its hacking simulations, only to learn later that the name unintentionally matched the domain of a real company. That led the model to “consider taking offensive action against” the real company in multiple training runs. Irregular said this was due to “human oversight,” and that they typically do a background check to ensure they’re not using a real company for cybersecurity tests. The instructions provided to the model also included the target’s name and “internal addresses within our ne

2. update from cyberpress.org

   Frontier AI Models Take Offensive Actions Against Real-World Systems During Cyber Tests

   cyberpress.org · 56d ago · August 18th, 2026

   Frontier AI models were observed taking offensive actions against real-world internet systems after an evaluation environment unintentionally allowed them to cross its intended containment boundary. Irregular said the issue stemmed from a single cyber-evaluation scenario and had been remediated before its initial public disclosure. The company emphasized that subsequent reports concerned the same underlying incident, not separate breaches, and said it found no evidence that a customer system was compromised or customer data was leaked. Irregular conducts pre-deployment testing for frontier AI labs, running thousands of simulations intended to determine whether models can plan and execute realistic multi-stage cyber campaigns . Frontier AI Models Take Offensive Actions Against Real-World Systems One advanced scenario assessed whether a model could help a malicious insider gain unauthorized access to sensitive data in a production database. The task simulated the full attack chain: reconnaissance, discovery and use of private keys, target-environment enumeration, data extraction, and attempts to evade detection. However, the fictional name selected for the test coincided with a little-known real internet domain. While most model runs remained within the intended environment, a small number of runs interpreted the real domain as part of the exerci

3. update from gbhackers.com

   AI Agents Gain Unintended Internet Access During Cybersecurity Evaluations

   gbhackers.com · 56d ago · August 18th, 2026

   AI security evaluation firm has disclosed that several frontier AI models unintentionally accessed and acted against real internet-connected systems during controlled cybersecurity testing. Irregular stated that […] The post AI Agents Gain Unintended Internet Access During Cybersecurity Evaluations appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform .