Does my text leave the browser?

No. All detection and redaction runs locally in JavaScript on this page. Nothing is uploaded or stored, which is the whole point — you scrub before any data reaches a third-party model.

Can it detect names and addresses?

Not reliably. Names and free-form addresses have no fixed pattern, so regex heuristics miss most of them. This tool targets structured identifiers like emails and phone numbers; always review the output and remove anything sensitive by hand.

What is the difference between the two replacement styles?

Numbered placeholders like [EMAIL_1] preserve which redactions refer to the same entity, useful when the LLM needs to track references. Uniform [REDACTED] is simpler when you only want everything gone.

Why did it not redact a phone number?

The phone matcher ignores digit runs shorter than seven digits to avoid mangling ordinary numbers in your text. Very short or unusually formatted numbers may slip through, so review the output.

Prompt PII Scrubber — Gera Tools

Prompt PII scrubber

Before you paste a prompt into ChatGPT, Claude, or any API, it is worth stripping out the personal data you do not need to share. This tool detects common structured identifiers — emails, phone numbers, credit cards, SSNs, IP addresses, and URLs — and redacts them right in your browser. No text is uploaded; the scrubbing happens locally so the sensitive data never reaches a server in the first place.

How it works

You paste your prompt text, tick the categories you want redacted, and pick a replacement style: numbered placeholders such as [EMAIL_1] that preserve which matches refer to the same entity, or a uniform [REDACTED]. The tool runs a set of ordered regular expressions — URLs and emails first so the greedier phone matcher does not eat their digits — and reports how many items of each category it removed. The phone matcher ignores runs shorter than seven digits to avoid false positives.

Tips and notes

Regex is good at structured patterns but blind to names and addresses, which have no consistent shape — so treat the output as a first pass and remove any remaining sensitive details by hand before sending. Numbered placeholders are the better choice when the model needs to reason about the same person or account more than once, because the references stay distinguishable. Because everything stays on your machine, you can safely scrub even highly confidential text here; the tool’s value is precisely that the data never has to travel to be cleaned.