sublimehighRule

Attachment: HTML with emoji-to-character map

Detects inbound messages containing HTML attachments with an unusually high number of emojis in a list, sent from untrusted or suspicious senders who lack an established sending history or have previous malicious behavior.

MITRE ATT&CK

T1566 T1566.001 T1566.002 T1598 T1036 T1027 T1598.003 T1059

defense-evasioninitial-accessexecution

Detection Query

type.inbound
and any(attachments,
        (
          .file_extension in~ ("html", "htm", "shtml", "dhtml")
          or .file_type == "html"
          or .content_type in ("application/octet-stream", "text/html")
        )
        and regex.icount(file.parse_html(.).raw,
                         '[\x{1F300}-\x{1F5FF}\x{1F600}-\x{1F64F}\x{1F680}-\x{1F6FF}\x{1F700}-\x{1F77F}\x{1F780}-\x{1F7FF}\x{1F900}-\x{1F9FF}\x{2600}-\x{26FF}\x{2700}-\x{27BF}\x{2300}-\x{23FF}].{0,10},'
        ) > 10
)
and (
  (
    profile.by_sender().prevalence in ("new", "outlier")
    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
)

Data Sources

Email MessagesEmail HeadersEmail Attachments

Platforms

Raw Content

name: "Attachment: HTML with emoji-to-character map"
description: "Detects inbound messages containing HTML attachments with an unusually high number of emojis in a list, sent from untrusted or suspicious senders who lack an established sending history or have previous malicious behavior."
type: "rule"
severity: "high"
source: |
  type.inbound
  and any(attachments,
          (
            .file_extension in~ ("html", "htm", "shtml", "dhtml")
            or .file_type == "html"
            or .content_type in ("application/octet-stream", "text/html")
          )
          and regex.icount(file.parse_html(.).raw,
                           '[\x{1F300}-\x{1F5FF}\x{1F600}-\x{1F64F}\x{1F680}-\x{1F6FF}\x{1F700}-\x{1F77F}\x{1F780}-\x{1F7FF}\x{1F900}-\x{1F9FF}\x{2600}-\x{26FF}\x{2700}-\x{27BF}\x{2300}-\x{23FF}].{0,10},'
          ) > 10
  )
  and (
    (
      profile.by_sender().prevalence in ("new", "outlier")
      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
  )

attack_types:
  - "Credential Phishing"
tactics_and_techniques:
  - "Evasion"
  - "HTML smuggling"
  - "Impersonation: Brand"
  - "Scripting"
  - "Social engineering"
detection_methods:
  - "File analysis"
  - "HTML analysis"
  - "Javascript analysis"
  - "Sender analysis"
id: "3119d086-13b9-549c-85b9-8117beaded4a"