Attachment: QR code with credential phishing indicators

type.inbound
and (
  1 <= length(attachments) < 3
  or (
    // if there are more than three attachments
    3 <= length(attachments) < 20
    // there are only pngs and pdf/docx
    and length(distinct(map(attachments, .file_extension))) == 2
    and all(distinct(map(attachments, .file_extension)),
            . in ('png', 'pdf', 'docx')
    )
    and (
      // multiple attachments mention common brands or other common common filenames
      (
        length(filter(attachments,
                      strings.icontains(.file_name, 'adobe')
                      or strings.icontains(.file_name, 'office')
                      or strings.icontains(.file_name, 'appstore')
                      or strings.icontains(.file_name, 'google')
                      or strings.icontains(.file_name, 'padlock')
                      or regex.icontains(.file_name, '\bdoc\b')
               )
        ) > 3
      )
      // the attachment name contains the SLD of a recipient
      or any(filter(attachments, .file_extension in ('pdf', 'docx')),
             any(filter(recipients.to, .email.domain.valid),
                 strings.icontains(..file_name, .email.domain.sld)
             )
      )
    )
  )
)

// Inspects image attachments for QR codes
and any(attachments,
        (
          .file_type in $file_types_images
          or .file_type == "pdf"
          or .file_extension in $file_extensions_macros
        )
        and (
          any(file.explode(.),
              .scan.qr.type == "url"
              and not .scan.qr.url.domain.domain == "geico.app.link"
              and (
                // pass the QR URL to LinkAnalysis
                any([ml.link_analysis(.scan.qr.url)],
                    .credphish.disposition == "phishing"

                    // any routing traverses via $suspicious_tld list
                    or any(.redirect_history, .domain.tld in $suspicious_tlds)

                    // effective destination in $suspicious_tld list
                    or .effective_url.domain.tld in $suspicious_tlds

                    // or the effective destination domain is in $abuse_ch_urlhaus_domains_trusted_reporters
                    or .effective_url.domain.root_domain in $abuse_ch_urlhaus_domains_trusted_reporters

                    // or any files downloaded are zips or executables
                    or any(.files_downloaded,
                           .file_extension in $file_extensions_common_archives
                           or .file_extension in $file_extensions_executables
                    )
                )
                or (

                  // or the QR code's root domain is a url_shortener
                  .scan.qr.url.domain.root_domain in $url_shorteners
                  or .scan.qr.url.domain.root_domain in $social_landing_hosts
                  and (
                    not (
                      any(ml.nlu_classifier(body.current_thread.text).intents,
                          .name == "benign"
                      )
                      or any(ml.nlu_classifier(body.current_thread.text).entities,
                             .name == "disclaimer"
                      )
                    )
                    or not any(attachments,
                               any(file.explode(.),
                                   any(ml.nlu_classifier(.scan.ocr.raw).intents,
                                       .name == "benign"
                                   )
                               )
                    )
                    // the QR code contains the email address of a recipient
                    or (
                      any(filter(recipients.to, .email.domain.valid),
                          strings.icontains(..scan.qr.url.url, .email.email)
                      )
                    )
                  )

                  // exclude google maps
                  and not strings.starts_with(.scan.qr.url.url,
                                              'https://goo.gl/maps'
                  )
                  and not strings.starts_with(.scan.qr.url.url,
                                              'https://maps.app.goo.gl'
                  )
                )

                // the QR code url is a bing open redirect
                or (
                  .scan.qr.url.domain.root_domain == 'bing.com'
                  and .scan.qr.url.path =~ '/ck/a'
                )
                // QR code contains non ascii chars
                or regex.contains(.scan.qr.url.url, '[^\x00-\x7F]')
                or (

                  // usap-dc open redirect
                  .scan.qr.url.domain.root_domain == "usap-dc.org"
                  and .scan.qr.url.path =~ "/tracker"
                  and strings.starts_with(.scan.qr.url.query_params,
                                          "type=dataset&url=http"
                  )
                  // the QR code contains the email address of a recipient
                  // allowing for base64 encoded variants
                  or (
                    any(filter(recipients.to, .email.domain.valid),
                        strings.icontains(..scan.qr.url.url, .email.email)
                        or any(beta.scan_base64(..scan.qr.url.url,
                                                ignore_padding=true
                               ),
                               strings.icontains(., ..email.email)
                        )
                        or any(beta.scan_base64(..scan.qr.url.fragment,
                                                ignore_padding=true
                               ),
                               strings.icontains(., ..email.email)
                        )
                    )
                  )
                )
              )
          )
        )
)
and (
  (
    profile.by_sender_email().prevalence in ("new", "outlier")
    and not profile.by_sender_email().solicited
  )
  or (
    profile.by_sender_email().any_messages_malicious_or_spam
    and not profile.by_sender_email().any_messages_benign
  )
  or (
      sender.email.domain.domain in $org_domains
      and not coalesce(headers.auth_summary.dmarc.pass, false)
  )
)

// 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
)