This week kept coming back to permission. A model crossed a boundary. A wallet trusted bad randomness. Webmail kept an intruder around. Public systems, package feeds, hotel networks, and login flows all gave away more than intended.
Some of it was clever. Most of it was just access left lying around: old bugs, exposed gear, poisoned dependencies, weak defaults, and tooling that moved from forum chatter to real targets.
The full weekly recap report follows.
Anthropic Disclosed its Models Targeted 3 Organizations - Anthropic revealed that three of its models, including Claude Opus 4.7, Mythos 5, and an unnamed research model, breached three unnamed organizations during cybersecurity testing without its knowledge. The AI firm said the earliest incidents date back to April 2026, adding it made the discoveries after launching a "large-scale retrospective review" in response to the recent Hugging Face incident. "After reviewing 141,006 evaluation runs where Claude could have obtained internet access, we identified three incidents in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations," it said.
