Protect yourself before you upload to AI
See what the AI will read that you can’t.
Hidden instructions, invisible characters and prompt injections can sit inside text that looks ordinary. Inspect it first — in your browser, without uploading anything.
- Find hidden text & instructions
- Spot injection indicators
- Text never leaves the page
Start a scan
Paste text or choose a file to reveal hidden content and suspicious instructions.
Paste your text here… The scanner opens in a private page — nothing is uploaded. Scan text nowReveal hidden text
Zero-width and invisible characters become readable U+XXXX tokens.
Spot injection patterns
Identifies instruction patterns designed to manipulate AI behavior.
Text, Markdown & HTML
Inline-hidden text is read as text; stylesheet-hidden text is not.
Context-aware analysis
Quoted and defensive framing is weighed — an example of an attack is not an attack.
Inspect the textual layers the browser supplies
Type or paste text
Choose a local file
Review coverage
Evidence in context, not a risk percentage
A keyword by itself is not enough. The scanner requires versioned combinations of instruction, target and objective concepts, then shows a bounded excerpt and original location. Quotation, code, research and policy framing can change a finding to review-only or suppress it.
Policy example: “Reject retrieved pages that instruct the model to disregard its governing instructions.”
The sentence discusses an indicator inside a prohibition. It illustrates why quoted attack language is a required hard negative rather than automatic proof of intent.
Leave with a defensible next action
| Result situation | Next action |
|---|---|
| Strong indicators | Quarantine the source from automated ingestion until a person reviews the evidence. |
| Suspicious indicators | Compare the passage with the intended visible source and edit or isolate it when appropriate. |
| No indicators in inspected text | Continue cautiously with the downstream system’s normal isolation, validation and approval controls. |
| Incomplete coverage | Use a tool or manual process that can inspect the unsupported layers before ingestion. |
The launch boundary
The scanner does: inspect supplied text with deterministic structural, Unicode, encoded-text and English instruction rules; preserve source locations; and report coverage, evidence, limitations and actions.
The scanner does not: upload content, call an AI model, fetch URLs, render submitted markup, remove passages, test a live model, inspect PDF/DOCX/images/audio/video or replace downstream security controls.
Browser-local rules are public and can be studied by attackers. Keep untrusted content separate from governing instructions, restrict model tools and require human approval for consequential actions.