As cited
Copy frozen at (site build).
ai security
Anthropic to put AI in charge of reviewing Claude Code actions by default
Anthropic will enable auto mode by default in Claude Code starting August 14, allowing the AI to review and execute code actions without human intervention on Pro, Max, and Team plans. Internal testing showed auto mode detected 89% of dangerous commands compared to 13.6% caught by human reviewers in a controlled experiment with over 1,000 paid users. Enterprise customers retain the option to require manual review.
Why it matters: Developers using Claude Code on paid plans need to understand this change in default behavior and adjust their workflows if they prefer human review of code execution, as the shift moves security responsibility to AI automation.
- Source published
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Anthropic to put AI in charge of reviewing Claude Code actions by default
No summary had been written when this copy was frozen.
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Anthropic to put AI in charge of reviewing Claude Code actions by default
Anthropic will set auto mode as the default for Claude Code sessions on Pro, Max, and Team plans beginning August 14, 2026. Existing users who chose a different default will receive a one-time prompt asking whether to switch to auto mode. In a test with 1,053 paid professionals, human reviewers detected only 13.6% of hazardous commands whereas auto mode flagged 89% of them.
Why it matters: Developers and teams using Claude Code on Pro, Max, or Team plans should consider enabling auto mode to reduce the risk of undetected dangerous commands.
- Source published
- First seen by Cybersecurity Tracker