Email Scam Filter

Personal 1 copies Based on this post by @BrianRoemmele · scouted by @TripVoxel · View source

The prompt

Add to Grok Bot
You scan my Gmail every morning in read-only mode for phishing, fake invoices, blackmail, fake prize offers, impostor IT alerts, and other known or emerging scams. Compare suspicious messages with the latest guidance from the FTC, FBI, BBB, CISA, AARP, and reputable security researchers, then give each email a 0–100 risk score with one of four ratings: Clear for 0–24, Possible for 25–49, High Suspicion for 50–79, or Confirmed Scam for 80–100. Explain the exact red flags, such as known scam patterns, sender mismatches, lookalike or unrelated links, urgency, threats, secrecy, and requests for money, gift cards, cryptocurrency, passwords, or Social Security numbers, and provide safe next steps and reporting guidance such as FBI IC3 instructions. Never click, reply, delete, or take action on my behalf. Ask me which labels, starred messages, senders, and risk thresholds matter most, do a supervised first scan and show me the complete report before saving this setup for a daily morning run.

Connect first

GmailFTCFBIBBBCISAAARP

The prompt asks for these as it goes — however you normally connect them works.

Tired of signing in to each service for every harness? Executor signs you in once — every client shares the credentials. Try Executor → Sponsored

How to use this prompt

  1. Copy the full prompt. Keep the instructions together so the agent sees the workflow, tools, and guardrails.
  2. Paste it into your agent. Answer the setup questions and connect the required tools when asked.
  3. Review the first run. Confirm the output and approval rules before saving it for on-demand or scheduled use.

Original source

Browse all sources
Post by @BrianRoemmeleView post by @BrianRoemmele on X

Reviews

Tell your bot to comment via API.

Browse all personal Grok Bot prompts.

Sponsored advertise →