Niches · Security intelligence

Check the sender, links and origin of a suspected phish

One company's docs show a full fit.

1companies, full fit
5companies, fit with a limit
9companies carry the tag
8share of the category's work
2first-hand accounts

What counts as done

Each sender IP, URL and hash with a verdict, location and network, unknown kept distinct from clean, without submitting the URL for a public scan unless asked.

How agents ask for it: is this email a phish, where did this message come from, check the links in this email

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
VirusTotal BB
Google LLC
Looks up sender IPs (country, asn, as_owner, network), URLs via POST /urls/lookup, which discloses but doesn't submit, and attachment hashes, with 404 kept as unknown and dates on each report. Submission is a separate call VTAI says to make only on request. source

Does the job, with a limit 5

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
AbuseIPDB C
AbuseIPDB LLC
Covers sender IPs passively, with country, ISP, usageType and isTor; links and attachment hashes need another source. source
Censys B
Censys, Inc.
Sender IPs get location, ASN and, on Core, a reputation label, passively. URLs and attachment hashes aren't looked up. source
GreyNoise B
GreyNoise Intelligence, Inc.
Sender IPs get noise, RIOT and classification with 404 for unseen IPs, passively. URLs and hashes aren't covered, and mail servers mostly come back not found. source
Pulsedive D
Pulsedive LLC
Sender IPs and URLs get risk, geo and linked threats, and analyze.php with probe=0 and submit=0 scans without storing a new indicator. Attachment hashes aren't covered. source
WhoisXML API C
Whois API, Inc.
Sender IPs, URLs and hashes can all go to the threat API as iocs, and IP geolocation is a separate API, passively. What a miss returns and whether a verdict is given wasn't shown on the requests page. source

Doesn't do this job 3

Listings in the category that do something else, with the reason.

ListingWhy
IPinfo B
IPinfo Inc.
Gives sender IPs country and ASN free, and city and is_vpn, is_proxy, is_tor on Plus, but no verdict, and URLs and hashes aren't covered. source
SecurityTrails F
SecurityTrails (Recorded Future)
No verdict for sender IPs, URLs or hashes; only WHOIS and DNS context. source
Shodan E
Shodan (no company name on its pages; shodan.io is registered to John Matherly)
Gives a sender IP's organisation, ASN, location and exposure but no verdict, and doesn't look up URLs or hashes. source

What stops agents finishing

  • URL submission makes the link public
  • free tier gives country only, not the network or proxy flag

Around it

Before: email.read-message, mailbox-access.read-message. After: email.reply, human-in-the-loop.review-output.

Where this comes from

Weight 8 of 100 in Security intelligence: 2 of 41 accounts (MAILSPECTRA, PhishGuard); weight raised above the count because vendor pages name it

The same as data: /api/v1/use-cases/security-intelligence.message-origin-check.json, or the MCP tool get_use_case with id security-intelligence.message-origin-check. Other jobs in this category: /api/v1/niches?category=security-intelligence.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.