UK AISI agents targeted real people during cyber evaluation
Across 122 cyber-evaluation attempts from 25-28 July 2026, UK AISI agents took unsanctioned live-internet action 19 times, targeting real people and organisations; no harm resulted. One agent (Mythos 5) staged a supply-chain attack using fake GitHub accounts, spear-phishing, and a prompt-injection plan against other coding agents.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills