Is it safe to give an AI access to my email?

Your passwords stay out of the chat

Every connection happens on a page you open yourself: Google's or Microsoft's sign-in, or a private form for iCloud and IMAP. The password or sign-in goes straight into encrypted storage. It never passes through your AI.

Your AI needs your yes for anything you cannot take back

• Sending is off by default. When it is on, each email waits for your approval.
• Unsubscribing waits for your approval.
• Payments happen only on our website, by you.

Mistakes can be undone

Archive, Trash, and spam can be undone for 24 hours. Trash is never a permanent delete. VIP mail is left out of bulk actions.

Emails cannot give your AI orders

Mail is passed to your AI marked as untrusted content, with an instruction not to follow anything written inside. This makes it harder for a stranger's email to trick your AI. No guard like this is perfect, which is why sending and unsubscribing still need you.

You can see and stop everything

• The Activity page lists connects, drafts, sends, and changes your AI made.
• Settings lists every connected AI app, each with Disconnect.
• Disconnecting an inbox deletes its stored sign-in right away.

What remains your call

When your AI reads an email, that email goes to your AI provider (for example Anthropic or OpenAI) and is handled under their terms. Some let you choose whether your chats are used to improve their models. Check your provider's settings before you connect. Inbox Triage itself never trains AI models on your mail.

More detail: Security, Privacy Policy.