Claude Code's auto mode is safer than human review, Anthropic finds
Auto mode is now the default in Claude Code
Anthropic is making auto mode the default in Claude Code for Pro, Max, and Team plans, citing data showing it's safer than manual approval. In a study with 1,053 testers, humans caught only 13.6% of dangerous commands, while auto mode blocked 89%. Auto mode also reduces prompt injection risks and boosts developer productivity, with teams shipping 25% more PRs.
In a controlled experiment with 1,053 paid professional testers, human review caught just 13.6% of dangerous commands, while auto mode caught 89%.