Claude Watermark Checker

Scan any text for invisible characters and see exactly what is hiding in it — the codepoint, the character name, how many there are, and where they sit. Nothing is changed, and nothing is uploaded.

  • Detects 9 character categories
  • Decodes hidden messages
  • Exact Unicode codepoints
  • Free & unlimited

Text to scan

Paste or type some text above to scan it.

What the checker looks for

Short answer

The Claude Watermark Checker inspects every single character in your text and flags any that is not an ordinary, visible one. It reports the exact Unicode codepoint, the official character name and the count for each — and if a hidden message is encoded in the text, it decodes and displays it.

Most tools in this space give you a yes or no. That is not useful when you need to know what is in a document and whether it matters. A no-break space picked up from Microsoft Word is not the same thing as an invisible payload someone deliberately embedded, and a tool that reports both as “watermark detected” has told you nothing.

So the checker reports findings the way a diagnostic tool should: grouped by category, ranked by how serious they are, with the raw codepoints visible so you can verify anything yourself.

The nine categories

CategorySeverityWhat it means
Unicode tag charactersHighCan encode a complete hidden ASCII message.
Zero-width charactersHighFully invisible; can carry binary-encoded data.
Bidirectional controlsHighCan display text in a different order than stored.
HomoglyphsHighCyrillic or Greek letters posing as Latin ones.
Variation selectorsMediumInvisible modifiers; chainable to hide data.
Control charactersMediumNon-printing codes that break parsers.
Non-standard spacesMediumNarrow no-break, thin, em spaces and similar.
Styled Unicode lettersLowMathematical, fullwidth or decorative letterforms.
Typographic charactersLowCurly quotes, em dashes, ellipsis characters.

How to read the score

The score is a weighted summary, not a simple count. Ten curly quotes in a long article are unremarkable; a single Unicode tag character is not. The weighting reflects that, and the score is scaled by finding density so one stray character in a 5,000-word document does not get reported with the same alarm as fifty in a paragraph.

  • 0 — Clean. Every character is standard and visible.
  • 1–34 — Minor formatting artifacts. Typically curly quotes or a stray no-break space. Normal in text from Word, Docs or a PDF.
  • 35–69 — Suspicious characters found. Invisible or non-standard characters are present in a quantity worth looking at.
  • 70–100 — Watermark characters found. Characters with no ordinary reason to be in prose, or a decoded hidden payload.

Decoding hidden messages

Two techniques are common enough to decode automatically, and the checker handles both.

Unicode tag characters

The block from U+E0000 to U+E007F maps one-to-one onto ASCII — subtract 0xE0000 and you get a normal character back — while rendering as nothing at all. Any run of them is decoded and shown to you in full.

Zero-width binary

Zero-width space as 0, zero-width non-joiner as 1, eight bits to a byte. The checker only reports a decode when the result is clean printable ASCII of a believable length — a false claim that your text contains a secret message would be worse than staying quiet.

When to run a check

  • Before publishing AI-assisted content. Catch invisible characters before your CMS does something strange with them.
  • On text from an unknown source. Pasted from an email, a shared doc or a web page you do not control.
  • When something is broken and you cannot see why. A string comparison that fails, a search that finds nothing, a word count that is wrong, a CSV that will not parse.
  • When you have been sent a document to review. Invisible text can carry instructions aimed at automated systems that process it later.

Found something you want gone? The Claude Watermark Eraser strips every category listed here, with per-category control over what gets changed.

Frequently asked questions

What does the Claude Watermark Checker detect?

It scans text character by character and flags nine categories: zero-width characters, Unicode tag characters, bidirectional controls, homoglyph letters, variation selectors, control characters, non-standard spaces, styled Unicode letters, and typographic characters. For each one it reports the exact Unicode codepoint, the official character name, and how many times it appears.

Can it show me a hidden message inside my text?

Yes. If the text contains Unicode tag characters (U+E0000 to U+E007F), the checker decodes them back to ASCII and displays the hidden message in full. It also attempts to decode zero-width binary steganography, where zero-width spaces and non-joiners encode one bit each.

What does the score mean?

The score runs from 0 to 100 and weighs both what was found and how unusual it is. Zero-width characters and hidden payloads score far higher than curly quotes. A score of 0 means every character in your text is standard and visible. Above 70 means characters were found that have no ordinary reason to be there.

Is the checker different from the eraser?

They share the same detection engine. The checker reports what it finds and changes nothing; the Claude Watermark Eraser removes it. Use the checker when you want to inspect a document before deciding, and the eraser when you just want clean text.

Does my text get uploaded when I check it?

No. The scan runs inside your browser. Nothing you paste is transmitted to our server or stored anywhere.

Why does it flag characters in text I wrote myself?

Non-standard characters arrive from many places, not only AI tools. Word and Google Docs insert curly quotes and no-break spaces automatically. Copying from a PDF or a web page frequently brings zero-width characters along. A few findings in a human-written document is completely normal.