Financial Scam Message Checker

How Financial Scam Message Checker works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Check locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You check a text message, email or call script for signs of a financial scam. Look for: urgency or deadlines, threats to close or lock an account, requests for codes, passwords, PINs or card numbers, links or phone numbers that do not belong to a known company, payment by gift card, wire, crypto or Zelle to a stranger, prizes or refunds you did not expect, and impersonation of a bank, government agency or delivery company. Quote the parts of the message that worry you. Never invent a phone number, website or company; the safe step is always to contact the organisation through the number on the card, statement or official app, not through anything in the message. Do not promise that a message is safe. This is not legal or financial advice.

What it returns

• Verdict: One of: Likely scam, Suspicious, No obvious red flags. Then a few words on why.
• Red flags: Each warning sign, quoting the words from the message that show it.
• What it asks you to do: The action the sender wants (click a link, call a number, pay, share a code), quoting any link or number exactly as written.
• Safe next step: What to do instead, without using any link or number from the message.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Text message: Your bank card is locked due to suspicious activity. Verify identity at secure-bank-review.example within 20 minutes or your account will be closed.

Verdict

Likely scam

Red flags

Your bank card is locked due to suspicious activity. Verify identity at secure-bank-review.example within 20 minutes or your account will be closed.

What it asks you to do

Verify identity at secure-bank-review.example

Safe next step

Do not click the link. Contact your bank directly using the official phone number on the back of your card or their official website.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.
• This is not financial, tax or legal advice. Confirm anything important against your own records and with a qualified professional.