News Brief

SentinelLabs discovered a Rust-based macOS backdoor attributed to North Korea that embeds 38 fake system messages designed to trick AI-assisted malware triage into aborting or refusing analysis.

Anthropic has formally accused Alibaba of orchestrating a 2.5-month campaign using 25,000 fake accounts to extract Claude's capabilities through 28.8 million unauthorized interactions.

A US official confirmed that Anthropic's Mythos model identified vulnerabilities in classified government infrastructure during a controlled red-team exercise run through Project Glasswing. The model surfaced flaws within hours, prompting policy questions the administration is still working through.

Google DeepMind published a 35-page AI Control Roadmap on June 18 that openly frames its own AI agents as potential insider threats, deploying structural containment controls rather than relying on alignment training alone.

Anthropic analysed 832 accounts banned for malicious cyber activity and mapped 13,873 attacker actions to MITRE ATT&CK — finding that AI is shifting from initial access to post-compromise work, and that medium-to-high-risk actors grew from 33% to 56% in under a year.