Employees forward suspicious emails to IT and wait, unsure whether to click. Security reviews each one by hand, which is slow, and the genuinely dangerous ones can sit in the queue next to harmless newsletters.
sonnet4 daysGmailOpenAIVirusTotalSlack
Claude
84ROI
74Scale
$3.1k91Saved
ROI for
README.md
Why this subagent
Employees forward suspicious emails to IT and wait, unsure whether to click. Security reviews each one by hand, which is slow, and the genuinely dangerous ones can sit in the queue next to harmless newsletters.
This inspector reads the body, the headers, and even screenshots, checks links against threat feeds, and rates the phishing risk with the exact red flags spelled out. High-risk mail alerts security immediately, and the reporter hears back fast on whether it is safe. People get a clear answer instead of guessing, and the real threats surface right away.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Read the body, headers, and links, and check domains and attachments against threat feeds.
pending
Rate phishing risk and explain the specific red flags, like a spoofed domain or a fake login link.
pending
Alert security on high-risk mail and tell the reporter whether it is safe to act on.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given an email body and screenshots, return a phishing risk score with the specific signals that drove it and a recommended action.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.