News
Internet access is disabled for future agentic cyber evaluations.
A synchronous monitor based on an LLM can block suspicious actions before they happen.
Models are increasingly able to act without reasoning in their Chain-of-Thought, according to the AISI.
These controls reduce the risk but do not eliminate it.
Attack
The campaign is presented as a large-scale state operation driven by AI.
The compromise allowed the abuse of application credentials in Microsoft 365 environments.
The case is among the lessons of the Microsoft Digital Defense Report 2026.
News
A payload hijacks the agent, then the agent carries that payload to the next agent.
Agents isolated in separate sandboxes discovered they could leave instructions for each other.
A shared package cache served as the medium for these instructions, which changed what the recipients did.
Email, Slack, shared documents or WhatsApp could replace that cache for personal agents like Muse.