Attachment: Microsoft impersonation via PDF with link and suspicious language

name: "Attachment: Microsoft impersonation via PDF with link and suspicious language"
description: "Attached PDF contains a Microsoft-affilated logo, suspicious language or keywords, and a link. Known malware delivery method."
type: "rule"
severity: "high"
source: |
  type.inbound
  and (
    any(attachments,
        (.file_extension == "pdf" or .file_type == "pdf")
        and any(ml.logo_detect(.).brands, strings.starts_with(.name, "Microsoft"))
    )
  )
  and any(attachments,
          (.file_extension == "pdf" or .file_type == "pdf")
          and any(file.explode(.),
                  (
                    length(filter([
                                    "password",
                                    "unread messages",
                                    "Shared Documents",
                                    "expiration",
                                    "expire",
                                    "expiring",
                                    "kindly",
                                    "renew",
                                    "review",
                                    "emails failed",
                                    "kicked out",
                                    "prevented",
                                    "storage",
                                    "required now",
                                    "cache",
                                    "qr code",
                                    "security update",
                                    "invoice",
                                    "retrieve",
                                    'engine failed',
                                    'OneDrive Error',
                                    'problem connecting',                                  
                                    'secure file',
                                    'access'
                                  ],
                                  strings.icontains(..scan.ocr.raw, .)
                           )
                    ) >= 2
                    or any(ml.nlu_classifier(.scan.ocr.raw).intents,
                           .name == "cred_theft" and .confidence == "high"
                    )
                  )
                  and (length(.scan.url.urls) > 0 or length(.scan.pdf.urls) > 0)
          )
  )
  and (
    not any(headers.hops,
            .authentication_results.compauth.verdict is not null
            and .authentication_results.compauth.verdict == "pass"
            and sender.email.domain.domain in (
              "microsoft.com",
              "sharepointonline.com"
            )
    )
  )
  and (
    not profile.by_sender().solicited
    or (
      profile.by_sender().any_messages_malicious_or_spam
      and not profile.by_sender().any_messages_benign
    )
  )
  
  // 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
  )
  and not profile.by_sender().any_messages_benign

tags:
  - "Malfam: Pikabot"
attack_types:
  - "Credential Phishing"
  - "Malware/Ransomware"
tactics_and_techniques:
  - "Image as content"
  - "Impersonation: Brand"
  - "PDF"
  - "Scripting"
  - "Social engineering"
detection_methods:
  - "Computer Vision"
  - "File analysis"
  - "Header analysis"
  - "Natural Language Understanding"
  - "Sender analysis"
id: "70d41c7f-19ba-5a4d-9eb6-3682eb655314"