Cloud storage impersonation with credential theft indicators

name: "Cloud storage impersonation with credential theft indicators"
description: "Detects messages impersonating cloud storage services that contain hyperlinked images leading to free file hosts, where message screenshots reveal high-confidence credential theft language and storage-related urgency tactics."
type: "rule"
severity: "medium"
source: |
  type.inbound
  and 0 < length(body.current_thread.links) < 10
  and any([subject.subject, sender.display_name],
          regex.icontains(., "(?:cloud|storage|mailbox|account|system|service)")
  )
  and any(ml.nlu_classifier(beta.ocr(file.message_screenshot()).text).intents,
          .name == "cred_theft" and .confidence == "high"
  )
  and not any(ml.nlu_classifier(beta.ocr(file.message_screenshot()).text).topics,
              .name == "Customer Service and Support" and .confidence == "high"
  )
  and regex.icontains(beta.ocr(file.message_screenshot()).text,
                      "storage.{0,50}full",
                      "free.{0,50}upgrade",
                      "storage.{0,50}details",
                      "storage.{0,50}quot",
                      "(?:mailbox|account|cloud).{0,50}(?:at risk|storage|disabled)"
  )
  and not strings.ilike(beta.ocr(file.message_screenshot()).text, "*free plan*")
  and (
    any(body.current_thread.links,
        // fingerprints of a hyperlinked image
        .display_text is null
        and .display_url.url is null
        and .href_url.domain.domain not in $tenant_domains
        and (
          .href_url.domain.root_domain in $free_file_hosts
          or .href_url.domain.root_domain in $url_shorteners
          or network.whois(.href_url.domain).days_old < 365
          or .href_url.domain.root_domain == "beehiiv.com"
          or (
            strings.icontains(.href_url.path, '.html')
            and coalesce(.href_url.domain.root_domain, "null") != sender.email.domain.root_domain
          )
        )
    )
  )
  // and the sender is not from high trust sender root domains
  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
  )
attack_types:
  - "Credential Phishing"
tactics_and_techniques:
  - "Free file host"
  - "Image as content"
  - "Impersonation: Brand"
  - "Social engineering"
detection_methods:
  - "Computer Vision"
  - "Content analysis"
  - "Header analysis"
  - "Natural Language Understanding"
  - "Optical Character Recognition"
  - "Sender analysis"
  - "URL analysis"
id: "4c20f72c-0045-518c-8157-7dad5f196ecc"