Get a daily scam check on your inbox
A read-only bot reads your new email each morning and gives each suspicious message a risk score and the red flags.
What the bot does
- Every morning, reads the new mail in your inbox. It can only read; it can't change anything.
- Checks each message for phishing, fake invoices, impostor “IT” alerts and prize scams.
- Keeps up with the latest scam alerts from public sources.
- Gives each suspicious email a risk level and the exact red flags, like a lookalike link.
What you end up with
A morning list: “Confirmed scam / High suspicion / Possible / Clear”, with what to do next.
Copy-paste prompt
Fill in the [brackets]. Then paste it into any tool below.
Every morning at 7am, check new emails in my inbox for scams: phishing, fake invoices, fake prize offers, blackmail emails and fake 'IT department' alerts. For each suspicious email give a risk level (Confirmed scam / High suspicion / Possible / Clear), the exact red flags (sender address, lookalike links, urgency, payment requests) and safe next steps. You are read-only: never click links, never reply, never delete.
Tools that can do it today
- agentGrok Bot (personal agents)Shared as a ready-made bot templateCheck plan requirements in xAI's docs
- agentGemini SparkGoogle AI Pro and Ultra subscribers in select countries
- agentClaude CoworkCheck plan requirements on Anthropic's help page
- chatChatGPTPaste in one suspicious email at a timeFree plan; paid plans add more
Plans and limits change; check each tool's page.
Watch out
- Keep it read-only. It should never click links or reply.
- A bot can miss scams too. If in doubt, call the company using a number you already trust.
Questions people ask
Which AI tools can do this?
Grok Bot (personal agents), Gemini Spark, Claude Cowork or ChatGPT can do this today. Paste the copy-paste prompt on this page into any of them and fill in the [brackets].
How hard is it to set up?
It's rated Easy. Start with the steps under “What the bot does”.
What should I watch out for?
Keep it read-only. It should never click links or reply.
Sources
Last checked Oct 20, 2026. Self-reported results from posts are the poster's own claims.