>_ have you seen this? · August 29, 2026
Researchers broke Claude Code's new auto-pilot safety net
Turned on autopilot for your coding agent yet? Here's how it gets tricked.
Security researchers at Embrace The Red demonstrated that Claude Code's Auto Mode—the safety system meant to protect users from malicious prompts while the agent runs unattended—can be bypassed. This comes right after Anthropic made Auto Mode the default behavior for Claude Code.
What this means for your business
If you've let Claude Code run on autopilot in your repo, assume it can be tricked into running commands you didn't approve, and review its changes before you trust the 'safety' layer.
Wondering how this applies to your workflow? That's a short conversation.
Book a consultation →