Attachment: Callback phishing solicitation via pdf file

type.inbound
and (
  not profile.by_sender().solicited
  or (
    profile.by_sender().any_messages_malicious_or_spam
    and not profile.by_sender().any_messages_benign
  )
)

// single attachment
and length(attachments) == 1

// sender is freemail
and (
  sender.email.domain.root_domain in $free_email_providers
  // the sender is a common service, which has likely been sent through a DL
  or (
    sender.email.domain.root_domain in $tranco_50k
    and all(recipients.to, .email.domain.domain not in $org_domains)
  )
)
// the attachment is a pdf with less than 3 pages, and at least 60 ocr chars
and any(attachments,
        (
          .file_extension == "pdf"
          // get the length of the attached pdf
          and any(file.explode(.),
                  .depth == 0
                  and .scan.exiftool.page_count < 3
                  and (
                    not (
                      strings.istarts_with(.scan.exiftool.producer,
                                           "Aspose.Words for Java"
                      )
                      and (
                        .scan.exiftool.creator == "Anusha T"
                        or any(.scan.exiftool.fields,
                               .key == "Author" and .value == "Anusha T"
                        )
                      )
                    )
                    or .scan.exiftool.producer is null
                    or .scan.exiftool.creator is null
                  )
          )
          // negate ML matches to "Professional and Career Development" - tuning resume FPs
          and not (
            any(beta.ml_topic(coalesce(body.html.display_text, body.plain.raw)).topics,
                .name == "Professional and Career Development"
                and .confidence == "high"
            )
            or (
              (
                any(attachments,
                    .file_type == 'pdf'
                    and any(file.explode(.),
                            any(beta.ml_topic(.scan.ocr.raw).topics,
                                .name == "Professional and Career Development"
                                and .confidence == "high"
                            )
                    )
                )
              )
            )
          )
          // check that any _single_ result in the file.explode matches these conditions
          // a second file.explode is required because the OCR is generated at a different depth within 
          // the file.explode results
          and (
            any(file.explode(.),
                length(.scan.ocr.raw) > 60
                // 4 of the following strings are found        
                and 4 of (
                  // this section is synced with attachment_callback_phish_with_pdf.yml and body_callback_phishing_no_attachment.yml
                  strings.icontains(.scan.ocr.raw, "purchase"),
                  strings.icontains(.scan.ocr.raw, "payment"),
                  strings.icontains(.scan.ocr.raw, "transaction"),
                  strings.icontains(.scan.ocr.raw, "subscription"),
                  strings.icontains(.scan.ocr.raw, "antivirus"),
                  strings.icontains(.scan.ocr.raw, "order"),
                  strings.icontains(.scan.ocr.raw, "support"),
                  strings.icontains(.scan.ocr.raw, "help line"),
                  strings.icontains(.scan.ocr.raw, "receipt"),
                  strings.icontains(.scan.ocr.raw, "invoice"),
                  strings.icontains(.scan.ocr.raw, "call"),
                  strings.icontains(.scan.ocr.raw, "helpdesk"),
                  strings.icontains(.scan.ocr.raw, "cancel"),
                  strings.icontains(.scan.ocr.raw, "renew"),
                  strings.icontains(.scan.ocr.raw, "refund"),
                  regex.icontains(.scan.ocr.raw, "(?:reach|contact) us at"),
                  strings.icontains(.scan.ocr.raw, "+1"),
                  strings.icontains(.scan.ocr.raw, "amount"),
                  strings.icontains(.scan.ocr.raw, "charged"),
                  strings.icontains(.scan.ocr.raw, "crypto"),
                  strings.icontains(.scan.ocr.raw, "wallet address"),
                  regex.icontains(.scan.ocr.raw, '\$\d{3}\.\d{2}\b'),
                  regex.icontains(.scan.ocr.raw,
                                  '(\+[ilo0-9]|1.(\()?[ilo0-9]{3}(\))?\D[ilo0-9]{3}\D[ilo0-9]{4})',
                                  '\+?([ilo0-9]{1,2})?\s?\(?\d{3}\)?[\s\.\-⋅]{0,5}[ilo0-9]{3}[\s\.\-⋅]{0,5}[ilo0-9]{4}'
                  ),
                )
                and (
                  // this section is synced with attachment_callback_phish_with_img.yml and body_callback_phishing_no_attachment.yml
                  regex.icontains(.scan.ocr.raw,
                                  '(p.{0,3}a.{0,3}y.{0,3}p.{0,3}a.{0,3}l|ma?c.?fee|n[o0]rt[o0]n|geek.{0,5}squad|ebay|symantec|best buy|lifel[o0]c|secure anywhere|starz|utilities premium|pc security|at&t)'
                  )
                  // suspicious attachment name from the attachment object not file.explode() output
                  or regex.icontains(..file_name, 'INV(?:_|\s)?\d+(.pdf)$')
                )
                // Negate bank statements
                and not (
                  2 of (
                    strings.icontains(.scan.ocr.raw, "opening balance"),
                    strings.icontains(.scan.ocr.raw, "closing balance"),
                    strings.icontains(.scan.ocr.raw, "direct debit"),
                    strings.icontains(.scan.ocr.raw, "interest"),
                    strings.icontains(.scan.ocr.raw, "account balance"),
                  )
                )
            )
            // this section is synced with attachment_callback_phish_with_img.yml and body_callback_phishing_no_attachment.yml
            or any(ml.logo_detect(.).brands,
                   .name in (
                     "PayPal",
                     "Norton",
                     "GeekSquad",
                     "Ebay",
                     "McAfee",
                     "AT&T"
                   )
            )
          )
        )
)
and (
  (
    (
      length(headers.references) > 0
      or not any(headers.hops,
                 any(.fields, strings.ilike(.name, "In-Reply-To"))
      )
    )
    and not (
      (
        strings.istarts_with(subject.subject, "RE:")
        or strings.istarts_with(subject.subject, "RES:")
        or strings.istarts_with(subject.subject, "R:")
        or strings.istarts_with(subject.subject, "ODG:")
        or strings.istarts_with(subject.subject, "答复:")
        or strings.istarts_with(subject.subject, "AW:")
        or strings.istarts_with(subject.subject, "TR:")
        or strings.istarts_with(subject.subject, "FWD:")
        or regex.imatch(subject.subject,
                        '(\[[^\]]+\]\s?){0,3}(re|fwd?|automat.*)\s?:.*'
        )
      )
    )
  )
  or (length(headers.references) == 0 or length(body.current_thread.text) < 10)
)