Documentation

← All agent examples

Check a suspicious email for phishing

Staff forward a suspicious email, with screenshots if they have them, and get a reply rating it phishing, suspicious or looks safe, with the reasons: sender and header oddities, where the links really go, and pressure tricks. The agent opens only the main site of each linked domain (for example https://example.com), never the link itself, to see what is there. This is an AI review, not a reputation or blocklist lookup, and "looks safe" is not a guarantee.

Security
Engineering and IT
phishing
suspicious email
scam
spoofing
email security
security awareness
report phishing
links

How it starts

When an email arrives.

Accepts files: Screenshots, Other files (ignored)

What it needs

No knowledge base, memory bank or connection to create first.

Steps

List the linked domains

Prompt Call

For each linked domain

For Each

For each item:

Open the domain's main site

Web Fetch

Describe what the domain hosts

Prompt Call

Keep the note

Item Value

Assess the email

Prompt Call

Parse and validate the verdict

Extract Content

Reply with the verdict

Send Email