This free checker shows whether text is safe to paste into an AI chatbot. Paste what you are about to send, and it marks anything that looks like an email address, phone number, card or bank number, ID number, password or API key, then gives you a cleaned copy with placeholders instead.
The check runs in your browser. The text you paste is never sent anywhere, saved or logged: close the tab and it is gone.
This checker needs JavaScript. Without it, read your text against the list under “What to keep out of every chat” below before you paste it.
What does the checker look for?
The plain point: it looks for the shape of private details, such as the pattern of a card number or an email address. It cannot tell what is secret to you.
- Passwords and PINs written after words such as “password:” or “PIN”.
- API keys and access tokens in the common formats, such as keys that start
sk-. - Card numbers, checked with the same digit test card companies use, so most random numbers are not flagged.
- Bank account numbers in the international IBAN format, also checked with their built-in test.
- ID numbers: US Social Security and UK National Insurance formats, and numbers labelled as a passport or licence.
- Email addresses, phone numbers, street addresses, dates of birth and IP addresses.
Each flagged item gets a short reason, and the cleaned copy swaps it for a label such as [EMAIL 1] or [CARD 1], so the chatbot can still follow your text.
A helper, not a guarantee. It catches the obvious numbers and codes. Names, health details and company secrets have no fixed pattern, so you still need to read your text once yourself.
What to keep out of every chat
The plain point: leave out anything that could hurt you, or someone else, if a stranger at the company read it or it leaked.
Canada’s privacy regulator sums it up: “do not share sensitive or identifiable personal information” and “do not share personal information about other people”.1 Anthropic’s help page for Claude names financial information, health records, passwords and confidential documents,2 and Google asks Gemini users not to enter anything confidential they would not want a reviewer to see.3
- Passwords and login codes, including one-time codes sent to your phone.
- Card and bank numbers. No chatbot needs them to help you.
- ID numbers, such as a social security, passport or driving licence number.
- Medical details. Ask the general question, without your name or records attached.
- Work secrets: client files, contracts, unreleased plans, anything your employer has not cleared for AI.
- Other people’s details, and anything at all about children.
If you need help with something personal, change the names and details first, as the Canadian regulator suggests. The placeholders this checker adds do that for the parts it can spot.
What it cannot check
The plain point: some private things look like ordinary words.
- Names of people, companies and places. “Sam” could be anyone, so the checker does not guess.
- Health, money and family details written in sentences, such as “my diagnosis came back”.
- Confidential work content: a draft contract or a sales figure looks like any other text.
- Numbers in unusual formats, such as ID numbers from countries whose format it does not know.
- Photos and files. It checks pasted text only.
For what happens to a chat after you send it, and how to turn off training or use a temporary chat, see Staying safe with AI and What happens to what you type.
Questions people ask
Does this tool send my text anywhere?
No. The check is a small script that runs inside this page in your browser. There is nothing for it to send the text to, and it does not save it, not even in your browser’s storage.
If nothing is flagged, is my text safe?
Not necessarily. “Nothing flagged” means no emails, numbers or codes in the formats it knows. Read the text once more for names, health details and work information before you paste it.
I already pasted a password into a chatbot. What now?
Change that password straight away, and anywhere else you used it, and turn on two-step sign-in if the account offers it. You can also delete the chat, but treat the password as known.
Is it safe to paste work documents into ChatGPT or Claude?
Only if your employer allows it. Many companies have rules on which AI tools staff may use and what they can paste in. AI at work for beginners explains how to check.
More free tools
The prompt checker shows what a chatbot prompt is missing, and the word and token counter estimates how long your text is in tokens. All of them are on the free tools page.
Related on this site: Pasted Something Private Into ChatGPT?
- 1Office of the Privacy Commissioner of Canada, Your privacy and AI chatbots, date modified 6 May 2025, read at source 5 Oct 2026“do not share sensitive or identifiable personal information”; “do not share personal information about other people”; “never share pictures or personal information of minors”; “alter personal details, for example, use aliases for names, change any identifiable details”. ↑
- 2Claude Help Center, I would like to input sensitive data into my chats with Claude. Who can view my conversations?, 22 May 2026, read at source 5 Oct 2026“we also recommend being thoughtful about sharing highly sensitive personal details such as: Financial information (SSN, credit card numbers, bank account details); Health records or medical information; Passwords or private login credentials; Confidential business or personal documents”. ↑
- 3Google, Gemini Apps Privacy Hub, read at source 1 Oct 2026“Please don’t enter confidential information that you wouldn’t want a reviewer to see or Google to use to improve our services”. ↑
Free printable AI cheat sheets, and AI news every week.
Sixteen one-page AI guides and checklists in one free PDF, no sign-up. And if you want to keep up, the newsletter covers what changed in AI each week, in plain English, with the sources.
SUBSCRIBE FREE ↗ GET THE CHEAT SHEET PACK