Link: Credential harvesting with excess padding evasion

type.inbound
// CTA link with action-oriented display text pointing to a different domain than the sender
and any(body.current_thread.links,
        regex.icontains(.display_text,
                        '(?:open|sign.?in|log.?in|retain|credential|secure|confirm|accept|release|review|document)'
        )
        and .href_url.domain.root_domain != sender.email.domain.root_domain
        and not regex.icontains(.display_text, 'open source')
)
// tall rendered email with low word density
and beta.parse_exif(file.message_screenshot()).image_height > 1500
and beta.parse_exif(file.message_screenshot()).image_height * 100 / regex.count(body.html.display_text,
                                                                                '\S+'
) > 500
// html whitespace stuffing patterns
and (
  // bare div-br blocks repeated 30+ times
  regex.icontains(body.html.raw, '(?:<div>\s*<br\s*/?\s*>\s*</div>\s*){30,}')
  // style div-br blocks repeated 20+ times
  or regex.icontains(body.html.raw,
                     '(?:<div\s+style="[^"]+"\s*[^>]*>\s*<br\s*/?\s*>\s*</div>\s*){20,}'
  )
  // attributed empty div-nbsp blocks repeated 20+ times (styled/classed empty divs, e.g. Outlook Aptos)
  // requires an attribute to avoid bare <div>&nbsp;</div> newsletter spacers
  or (
    regex.icontains(body.html.raw,
                    '(?:<div\s+[^>]+>\s*(?:&nbsp;|&#160;)\s*</div>\s*){20,}'
    )
    // exclude collapsed/hidden empty divs (display:none, font-size:0, line-height:0)
    // these render to zero height and are ESP preheader artifacts, not visible stuffing
    and not regex.icontains(body.html.raw,
                            '(?:<div\s+[^>]*(?:display\s*:\s*none|font-size\s*:\s*0|line-height\s*:\s*0)[^>]*>\s*(?:&nbsp;|&#160;)\s*</div>\s*){20,}'
    )
  )
  // p-nbsp blocks repeated 25+ times
  or regex.icontains(body.html.raw,
                     '(?:<p>\s*(?:&nbsp;|&#160;)\s*</p>\s*){25,}'
  )
  // css margin-top pushdown >= 1500px
  or (
    regex.icontains(body.html.raw,
                    'margin-top\s*:\s*(?:1[5-9]\d{2}|[2-9]\d{3}|\d{5,})px'
    )
    and not regex.icontains(body.html.raw,
                            'position\s*:\s*absolute[^"]*margin-top\s*:\s*(?:1[5-9]\d{2}|[2-9]\d{3}|\d{5,})px'
    )
    and not regex.icontains(body.html.raw,
                            'margin-left\s*:\s*\d{3,}px[^"]*margin-top\s*:\s*(?:1[5-9]\d{2}|[2-9]\d{3}|\d{5,})px'
    )
  )
)