Fake message thread with a suspicious link and engaging language from an unknown sender

type.inbound
and length(body.links) < 10

// fake thread check
and (subject.is_reply or subject.is_forward)

// Check for the Presence of References or In-Reply-To properties
and (
  (length(headers.references) == 0 and headers.in_reply_to is null)
  or headers.in_reply_to is null
)

// sender's domain is not in body, and body has > 0 links
and length(body.links) > 0
and sender.email.domain.root_domain not in $free_email_providers
and not any(body.links,
            .href_url.domain.root_domain == sender.email.domain.root_domain
)

// unusual sender (email address rarely sends to your organization)
and sender.email.email not in $sender_emails

// unusual sender domain (domain rarely sends to your organization)
and sender.email.domain.domain not in $sender_domains
and 4 of (
  // language attempting to engage
  (
    any(ml.nlu_classifier(body.current_thread.text).entities,
        .name == "request"
    )
    and any(ml.nlu_classifier(body.current_thread.text).entities,
            .name == "financial"
    )
  ),

  // invoicing language
  any(ml.nlu_classifier(body.current_thread.text).tags, .name == "invoice"),

  // urgency request
  any(ml.nlu_classifier(body.current_thread.text).entities, .name == "urgency"),

  // cred_theft detection
  any(ml.nlu_classifier(body.current_thread.text).intents,
      .name == "cred_theft" and .confidence in~ ("medium", "high")
  ),

  // commonly abused sender TLD
  strings.ilike(sender.email.domain.tld, "*.jp"),

  // headers traverse abused TLD
  any(headers.domains, strings.ilike(.tld, "*.jp")),

  // known suspicious pattern in the URL path
  any(body.links, regex.match(.href_url.path, '\/[a-z]{3}\d[a-z]')),

  // link display text is in all caps
  any(body.links, regex.match(.display_text, '[A-Z ]+')),

  // display name contains an email
  regex.contains(sender.display_name, '[a-z0-9]+@[a-z]+'),

  // Sender domain is empty
  sender.email.domain.domain == "",

  // sender domain matches no body domains
  all(body.links,
      .href_url.domain.root_domain != sender.email.domain.root_domain
  ),
)

// negate highly trusted sender domains unless they fail DMARC authentication
and (
  (
    sender.email.domain.root_domain in $high_trust_sender_root_domains
    and not headers.auth_summary.dmarc.pass
  )
  or sender.email.domain.root_domain not in $high_trust_sender_root_domains
)