Tag

#agent-safety

1 story tagged agent-safety.

Claude Code auto mode block rate for dangerous commands: human reviewers caught 13.6 percent, auto mode caught 89 percent. Prompt injection attack success rate was 0 percent for Claude models in auto mode versus 5.83 percent for GPT-5.6 Sol in Codex Auto-review.

Claude Code auto mode becomes default on August 14

Claude Code auto mode runs commands without per-step permission. It becomes the default August 14, 2026 for Pro, Max, and Team plans.

Lars Cornelissen · Aug 9, 2026