Pre-scan inbound email for phishing before other bots touch it
At a glance
Cary Scardina’s Grok Bot checks headers, links, and attachment hashes with open-source tools and pre-scans domains/downloads so humans and downstream agents never open the low-hanging phishing bait first. This workflow is listed under Grok-Bot, Email, Security, Phishing, Life-Admin.
DiMilan shares a standing instruction: have your main Grok Bot run a prompt-injection safety check across every bot that can read email, calendar, files, or web pages before those connectors stay live.
Security-minded user runs a Grok Bot that scans inbound email for phishing and social-engineering signals, checks headers, links, and attachment hashes against open-source tools, and pre-screens domains/downloads before humans or other bots open them.
After claiming a bot mailbox, one user kept Fastmail for calendar/contacts/notes and forwarded into Grok mail so the bot answers live instead of a 15-minute poll routine.
Users are spinning up a dedicated agent inbox: forward mail for it to act, CC it on threads for scheduling, and subscribe tools/newsletters to that address instead of a personal one.