Subagents run in their own isolated context window and return only a result to your main session — the intermediate work ...
Spam accounts overwhelmed my database. Claude found the weaknesses, Codex wrote the fixes, and I deployed a new defense.
Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results