ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

Researchers Forever Security found AI agents like OpenAI Codex and Claude Code executing malware via malicious AGENTS.md files in the Downloads folder. The attack abuses prompt injection to trick agents into downloading dangerous code or stealing session tokens without user consent, marking a new security liability for autonomous software.
Tap to vote and see what everyone thinks.
Summary by ByteBrief