Score every suspicious email 0 to 100 using this week's scam alerts
- Level Intermediate
- Setup1–3 hrs (estimated)
- Evidence Some evidence
- CostNot stated in source
- No-codeNo
What they did
A user built an Email Scam Filter in Grok Bot that checks his Gmail every morning for phishing, fake invoices, blackmail emails, fake prizes and fake "IT department" alerts. Before scanning, it reads the latest scam warnings from the FTC, FBI, BBB, CISA, AARP and security researchers, then gives each suspicious email a 0 to 100 risk score, the red flags it found and safe next steps. It's read-only: it never clicks, replies or deletes.
How it went
He says its very first scan found password-phishing emails sitting starred in his inbox.
Worth knowing
- Self-reported X post by the bot's author, who shares it as an add-on; no false-positive numbers. Another user later published a modified version with extra prompt-injection defenses.
Prompt
Cleaned version rewritten from the source — not a direct quote.
Every morning, read the latest scam warnings from [FTC, FBI, CISA, BBB, AARP]. Then scan my Gmail read-only for phishing, fake invoices, blackmail, fake prizes and impostor IT alerts. For each suspicious email give a 0-100 risk score (Confirmed Scam, High Suspicion, Possible or Clear), the exact red flags, and safe next steps, including how to report it. Never click, reply or delete anything.
Recommended
Try it in Grok Bot
- Copy the prompt (button below).
- Open Grok Bot chat and paste it. Replace any [bracketed] placeholders.
- Connect the listed tools (Gmail, Email) as connectors when Grok Bot asks.
- If the task repeats, ask: "Make this a daily routine."
Alternatives: the same prompt works in Claude, ChatGPT Agent, OpenClaw.
Set it up
Tools: Gmail, Email · Stack: Grok Bot
- Read the original source for full context.
- Connect the tools your agent needs.
- Paste the prompt and replace [bracketed] placeholders.
- Run once manually and check the output before scheduling it.
Generic suggested steps, not from the source.
Evidence
Self-reported X post by the bot's author, who shares it as an add-on; no false-positive numbers. Another user later published a modified version with extra prompt-injection defenses
Source: X · 2026-10-13 · Verified by us: not yet · Report broken or outdated