local.sco

flex是linux下一个很有用的高效的编译器工具

header FROM_STARTS_WITH_NUMS	From:addr =~ /^\d{6,}\S+\@/i
describe FROM_STARTS_WITH_NUMS	From: starts with many numbers

# note: anchored for speed
header FROM_HAS_MIXED_NUMS	From:addr =~ /^[a-z]+\d+[a-z]+\d+[a-z]+\w*\@/i
describe FROM_HAS_MIXED_NUMS	From: contains numbers mixed in with letters

header FROM_HAS_ULINE_NUMS	From =~ /_\S?(?:[a-z]+\w*?\d+|\d+\w*?[a-z]+)\w*\@/i
describe FROM_HAS_ULINE_NUMS	From: contains an underline and numbers/letters

# don't match US/Canada phone numbers: 10 digits optionally preceded by a "1"
header FROM_ALL_NUMS		From:addr =~ /^(?:\d{1,9}|[02-9]\d{10}|\d{12,})@/
describe FROM_ALL_NUMS		From numeric address (except US/Canada phones)

header FROM_OFFERS		From:addr =~ /\@\S*offers(?![eo]n\b)/i
describe FROM_OFFERS		From address is "at something-offers"

header FROM_NO_USER		From =~ /(?:^\@|<\@| \@[^\)<]*$|<>)/ [if-unset: [e-mail]]
describe FROM_NO_USER		From: has no local-part before @ sign

header TO_NO_USER		To =~ /(?:^\@|<\@| \@[^\)<]*$|<>)/ [if-unset: [e-mail]]
describe TO_NO_USER		To: has no local-part before @ sign

header TO_EMPTY			To =~ /^\s*$/ [if-unset: UNSET]
describe TO_EMPTY		To: is empty

header REPLY_TO_EMPTY		Reply-To =~ /^\s*$/ [if-unset: UNSET]
describe REPLY_TO_EMPTY		Reply-To: is empty

header TO_ADDRESS_EQ_REAL	To =~ /^\s*"([^"@]+\@[^"@]+)"\s+<\1>\s*$/i
describe TO_ADDRESS_EQ_REAL	To: repeats address as real name

# NOTE: this is what 100% valid undisclosed-recipients mails look like.
# If this gets a high score, that's a bug!
header UNDISC_RECIPS		To =~ /^undisclosed-recipients?:\s*;$/
describe UNDISC_RECIPS		Valid-looking To "undisclosed-recipients"

# also 100% valid
header FAKED_UNDISC_RECIPS	To =~ /undisclosed[_ ]*recipient(?:s[^:]|[^s])/i
describe FAKED_UNDISC_RECIPS	Faked To "Undisclosed-Recipients"

header PLING_QUERY		Subject =~ /\?.*!|!.*\?/
describe PLING_QUERY		Subject has exclamation mark and question mark

header SUBJ_HAS_SPACES		Subject =~ /(?:\s{6}|\t\s|\s\t)\S/
describe SUBJ_HAS_SPACES	Subject contains lots of white space

header MSGID_SPAM_99X9XX99	MESSAGEID =~ /^<\d\d\d\d\d\d[a-z]\d[a-z][a-z]\d\d\$[a-z][a-z][a-z]\d\d\d\d\d\$\d\d\d\d\d\d\d\d\@/
describe MSGID_SPAM_99X9XX99	Spam tool Message-Id: (99x9xx99 variant)

header MSGID_SPAM_ALPHA_NUM	MESSAGEID =~ /<[A-Z]{7}-000[0-9]{10}\@[a-z]*>/
describe MSGID_SPAM_ALPHA_NUM	Spam tool Message-Id: (alpha-numeric variant)

header MSGID_SPAM_CAPS		Message-ID =~ /^\s*<?[A-Z]+\@(?!(?:mailcity|whowhere)\.com)/
describe MSGID_SPAM_CAPS	Spam tool Message-Id: (caps variant)

header MSGID_SPAM_LETTERS	Message-Id =~ /<[a-z]{5,}\@(\S+\.)+\S+>/
describe MSGID_SPAM_LETTERS	Spam tool Message-Id: (letters variant)

header MSGID_SPAM_ZEROES	MESSAGEID =~ /<0000[0-9a-f]{8}\$0000[0-9a-f]{4}\$0000[0-9a-f]{4}\@/
describe MSGID_SPAM_ZEROES	Spam tool Message-Id: (12-zeroes variant)

header MSGID_NO_HOST            MESSAGEID =~ /\@>(?:$|\s)/m
describe MSGID_NO_HOST 		Message-Id has no hostname

header MSGID_OUTLOOK_INVALID	eval:check_outlook_message_id()
describe MSGID_OUTLOOK_INVALID	Message-Id is fake (in Outlook Express format)

header MSGID_YAHOO_CAPS		Message-ID =~ /<[A-Z]+\@yahoo.com>/
describe MSGID_YAHOO_CAPS	Message-ID has [e-mail]

header MSGID_FROM_MTA_HOTMAIL	Message-Id =~ /<MC\d{1,2}-F{1,2}\w{21,22}\@\S*hotmail\.com>/
describe MSGID_FROM_MTA_HOTMAIL	Message-Id was added by a hotmail.com relay

header MSGID_LONG		MESSAGEID =~ /<.{160,}>|<.{140,}\@|\@.{55,}>/m
describe MSGID_LONG		Message-ID is unusually long

header MSGID_SHORT		MESSAGEID =~ /^.{1,15}$|<.{0,4}\@/m
describe MSGID_SHORT		Message-ID is unusually short

header MSGID_MULTIPLE_AT	MESSAGEID =~ /<[^>]*\@[^>]*\@/
describe MSGID_MULTIPLE_AT	Message-ID contains multiple '@' characters

header DATE_SPAMWARE_Y2K	Date =~ /^[A-Z][a-z]{2}, \d\d [A-Z][a-z]{2} [0-6]\d \d\d:\d\d:\d\d [A-Z]{3}$/
describe DATE_SPAMWARE_Y2K	Date header uses unusual Y2K formatting

header INVALID_DATE		Date !~ /^\s*(?:(?i:Mon|Tue|Wed|Thu|Fri|Sat|Sun),\s+)?[0-3\s]?[0-9]\s+(?i:Jan|Feb|Ma[ry]|Apr|Ju[nl]|Aug|Sep|Oct|Nov|Dec)\s+(?:[12][901])?[0-9]{2}\s+[0-2]?[0-9](?:\:[0-5][0-9]){1,2}\s+(?:[AP]M\s+)?(?:[+-][0-9]{4}|UT|[A-Z]{2,3}T)(?:\s+\(.*\))?\s*$/ [if-unset: Wed, 31 Jul 2002 16:41:57 +0200]
describe INVALID_DATE		Invalid Date: header (not RFC 2822)

# allow +1300, NZ timezone
header INVALID_DATE_TZ_ABSURD	Date =~ /[-+](?:1[4-9]\d\d|[2-9]\d\d\d)$/
describe INVALID_DATE_TZ_ABSURD	Invalid Date: header (timezone does not exist)

header INVALID_TZ_CST		ALL =~ /[+-]\d\d[30]0(?<!-0600|-0500|\+0800|\+0930|\+1030)\s+(?:\bCST\b|\(CST\))/
describe INVALID_TZ_CST		Invalid date in header (wrong CST timezone)

header INVALID_TZ_EST		ALL =~ /[+-]\d\d[30]0(?<!-0500|-0300|\+1000|\+1100)\s+(?:\bEST\b|\(EST\))/
describe INVALID_TZ_EST		Invalid date in header (wrong EST timezone)

header INVALID_TZ_GMT		ALL =~ /[+-]\d\d[30]0(?<![+-]0000)\s+(?:\b(?:GMT|UTC)\b(?![\w+-])|\((?:GMT|UTC)\))/
describe INVALID_TZ_GMT		Invalid date in header (wrong GMT/UTC timezone)

header SUBJECT_ENCODED_TWICE	Subject:raw =~ /=\?\S+\?[BQ]\?.*=\?\S+\?[BQ]\?/i
describe SUBJECT_ENCODED_TWICE	Subject: MIME encoded twice

header ENGLISH_UCE_SUBJECT	Subject =~ /^[^0-9a-z]*adv(?:ert)?\b/i
describe ENGLISH_UCE_SUBJECT	Subject contains an English UCE tag

header JAPANESE_UCE_SUBJECT	Subject =~ /\e\$B.*(?:L\$>5Bz|EE;R%a!<%k)9-9p/
describe JAPANESE_UCE_SUBJECT	Subject contains a Japanese UCE tag

header KOREAN_UCE_SUBJECT	Subject =~ /[({[<][. ]*(?:\xbc\xba[. ]*\xc0\xce[. ]*)?(?:\xb1\xa4(?:[. ]*|[\x00-\x7f]{0,3})\xb0\xed|\xc1\xa4[. ]*\xba\xb8|\xc8\xab[. ]*\xba\xb8)[. ]*[)}\]>]/
describe KOREAN_UCE_SUBJECT	Subject: contains Korean unsolicited email tag

header RCVD_BY_IP	Received =~ /\bby\s+\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?<!127\.0\.0\.1)\b/
describe RCVD_BY_IP	Received by mail server with no name

header RCVD_BY_IP	Received =~ /\bby\s+\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?<!127\.0\.0\.1)\b/
describe RCVD_BY_IP	Received by mail server with no name

header FORGED_TELESP_RCVD	Received =~ /\.(?!br).. \(\d+-\d+-\d+-\d+\.dsl\.telesp\.net\.br /
describe FORGED_TELESP_RCVD	Contains forged hostname for a DSL IP in Brazil

# this, by comparison is more common: from was @hotmail.com, but it wasn't
header FORGED_HOTMAIL_RCVD2	eval:check_for_no_hotmail_received_headers()
describe FORGED_HOTMAIL_RCVD2 hotmail.com 'From' address, but no 'Received:'

header FORGED_EUDORAMAIL_RCVD	eval:check_for_forged_eudoramail_received_headers()
describe FORGED_EUDORAMAIL_RCVD	Forged eudoramail.com 'Received:' header found

header NONEXISTENT_CHARSET	Content-Type =~ /charset=.?DEFAULT/
describe NONEXISTENT_CHARSET	Character set doesn't exist

header X_PRIORITY_HIGH		X-Priority =~ /^1/
describe X_PRIORITY_HIGH	Sent with 'X-Priority' set to high

header X_MSMAIL_PRIORITY_HIGH	X-Msmail-Priority =~ /^High/
describe X_MSMAIL_PRIORITY_HIGH	Sent with 'X-Msmail-Priority' set to high

header MISSING_DATE             Date =~ /^UNSET$/ [if-unset: UNSET]
describe MISSING_DATE           Missing Date: header

header GAPPY_SUBJECT		Subject =~ /\b(?:[a-z]([-_. =~\/:,*!\@\#\$\%\^&+;\"\'<>\\])\1{0,2}){4}/i
describe GAPPY_SUBJECT		Subject: contains G.a.p.p.y-T.e.x.t

header PREVENT_NONDELIVERY	exists:Prevent-NonDelivery-Report
describe PREVENT_NONDELIVERY	Message has Prevent-NonDelivery-Report header

header X_IP			exists:X-IP
describe X_IP			Message has X-IP header

header X_LIBRARY		exists:X-Library
describe X_LIBRARY		Message has X-Library header

header X_MESSAGE_FLAG_ODD	ALL =~ /^X-Message-flag:/m
describe X_MESSAGE_FLAG_ODD	Message has X-Message-flag header (odd case)

header SUBJ_AS_SEEN		Subject =~ /\bAs Seen/i
describe SUBJ_AS_SEEN		Subject contains "As Seen"

header SUBJ_DOLLARS             Subject =~ /^\$[0-9.,]+\b/
describe SUBJ_DOLLARS           Subject starts with dollar amount

header SUBJ_FOR_ONLY 		Subject =~ /For Only/i
describe SUBJ_FOR_ONLY 		Subject contains "For Only"

header SUBJ_FREE_CAP		Subject =~ /FREE|F.R.E.E\b/
describe SUBJ_FREE_CAP		Subject contains "FREE" in CAPS

header SUB_FREE_OFFER           Subject =~ /^fre{2,}\b/i
describe SUB_FREE_OFFER         Subject starts with "Free"

header SUBJ_GUARANTEED          Subject =~ /^guaranteed|(?-i:GUARANTEE)/i
describe SUBJ_GUARANTEED        Subject GUARANTEED

header SUB_HELLO                Subject =~ /^hello\b/i
describe SUB_HELLO              Subject starts with "Hello"

header SUBJ_LIFE_INSURANCE	Subject =~ /life\s+insurance/i
describe SUBJ_LIFE_INSURANCE	Subject includes "life insurance"

header SUBJ_YOUR_DEBT		Subject =~ /Your (?:Bills|Debt|Credit)/i
describe SUBJ_YOUR_DEBT		Subject contains "Your Bills" or similar

header SUBJ_YOUR_FAMILY		Subject =~ /Your Family/i
describe SUBJ_YOUR_FAMILY	Subject contains "Your Family"

header SUBJ_YOUR_OWN		Subject =~ /Your Own/i
describe SUBJ_YOUR_OWN		Subject contains "Your Own"

header RCVD_FAKE_HELO_DOTCOM    Received =~ /^from (?:msn|yahoo|yourwebsite|lycos|excite|cs|aol|localhost|koreanmail|allexecs|mydomain|juno|eudoramail|compuserve|desertmail|excite|caramail)\.com \(/m
describe RCVD_FAKE_HELO_DOTCOM  Received contains a faked HELO hostname

header SUBJECT_DIET		Subject =~ /\bLose .*(?:pounds|lbs|weight)/i
describe SUBJECT_DIET		Subject talks about losing pounds

header EXTRA_MPART_TYPE         Content-Type =~ /(?:\s*multipart\/)?.* type=/i
describe EXTRA_MPART_TYPE       Header has extraneous Content-type:...type= entry

header TO_RECIP_MARKER          To =~ /\#recipient\#/
describe TO_RECIP_MARKER        To header contains 'recipient' marker

header MIME_BOUND_DD_DIGITS	Content-Type =~ /boundary=\"--\d+\"/
describe MIME_BOUND_DD_DIGITS	Spam tool pattern in MIME boundary

header MIME_BOUND_DIGITS_7	Content-Type =~ /boundary=\d{9}\.\d{13}/
describe MIME_BOUND_DIGITS_7	Spam tool pattern in MIME boundary

header MIME_BOUND_DIGITS_15	Content-Type =~ /boundary=\"\d{15,}\"/
describe MIME_BOUND_DIGITS_15	Spam tool pattern in MIME boundary

header MIME_BOUND_MANY_HEX	Content-Type =~ /boundary="[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12}"/
describe MIME_BOUND_MANY_HEX	Spam tool pattern in MIME boundary

header MIME_BOUND_RKFINDY       Content-Type =~ /boundary=\"=_NextPart_2rfkindysadvnqw3nerasdf\"/
describe MIME_BOUND_RKFINDY     Spam tool pattern in MIME boundary (rfkindy)

# note: the first alternation is anchored for speed
header TO_MALFORMED             To !~ /(?:^|[^\S"])(?:(?:\"[^\"]+\"|\S+)\@\S+\.\S+|^\s*.+:\s*;|^\s*\"[^\"]+\":\s*;|^\s*\([^\)]*\)\s*$|<\S+(?:\!\S+){1,}>|^\s*$)/ [if-unset: [e-mail]]
describe TO_MALFORMED           To: has a malformed address

header ADDR_FREE              From =~ /\b(?-i:F)ree(?-i:[ A-Z]).*</i
describe ADDR_FREE            From Address contains FREE

# common spam-dropping: To: C:\[e-mail]
header TO_TXT			To =~ /\.txt[\'\"]?\@/i
describe TO_TXT			Sent to a text file

header CHINA_HEADER             ALL =~ /\@china\.com/i
describe CHINA_HEADER           Involves 'china.com'

header WITH_LC_SMTP		Received =~ /\swith\ssmtp;\s/
describe WITH_LC_SMTP		Received line contains spam-sign (lowercase smtp)

header FROM_NO_LOWER		From:addr !~ /[a-z]/ [if-unset: [e-mail]]
describe FROM_NO_LOWER		From address has no lower-case characters

header SUBJ_BUY                 Subject =~ /^buy/i
describe SUBJ_BUY               Subject line starts with Buy or Buying

# seems to be ratware
header RCVD_AM_PM		Received =~ /; [A-Z][a-z][a-z], \d{1,2} \d{4} \d{1,2}:\d\d:\d\d [AP]M [+-]\d{4}/
describe RCVD_AM_PM		Received headers forged (AM/PM)

header X_ORIG_IP_NOT_IPV4	X-Originating-IP !~ /\[?(?:\d{1,3}\.){3}\d{1,3}\]?/ [if-unset: 0.0.0.0]
describe X_ORIG_IP_NOT_IPV4	X-Originating-IP doesn't look like IPv4 address

# match the format of a legit X-Auth-Warning header, and hit on fake ones
# normal: "e4e.oac.uci.edu: foo owned process doing -bs"
# fake: "bzgrdag, upaeqehv"
header X_AUTH_WARN_FAKED	X-Authentication-Warning !~ /(?:set sender to \S{2,80} using -f|owned process doing -bs|claimed to be|didn.t use HELO protocol)/ [if-unset: host.example.com: foo owned process doing -bs]
describe X_AUTH_WARN_FAKED	X-Authentication-Warning header looks faked

# host no longer exists according to administrator
header FAKE_OUTBLAZE_RCVD	Received =~ /\.mr\.outblaze\.com/
describe FAKE_OUTBLAZE_RCVD	Received header contains faked 'mr.outblaze.com'

# domains never longer used for email, confirmed by administrator
header FROM_NONSENDING_DOMAIN	From:addr =~ /\@(?:altavista\.com|eudora\.com)$/i
describe FROM_NONSENDING_DOMAIN	Message is from domain that never sends email

header SUBJ_2_NUM_PARENS        Subject =~ /^\(\d+\).*\(\d+\)\s*$/
describe SUBJ_2_NUM_PARENS      Subject contains common spam sign (2 numbers)

# thanks to David Ritz for passing this on; ready for post-3.0.0
header UNCLOSED_BRACKET		ALL =~ /\[\d+\r?\n/s
describe UNCLOSED_BRACKET	Headers contain an unclosed bracket

# some header rules
header ORG_MIME_TOOLS		Organization =~ /MIME-tools/
describe ORG_MIME_TOOLS		Organization is MIME-tools

header X_MIME_AUTOCONVERTED	X-MIME-Autoconverted =~ /Yes/
describe X_MIME_AUTOCONVERTED	Message has X-MIME-Autoconverted "Yes" header

header FROM_DOMAIN_NOVOWEL	From =~ /\@\S*[bcdfghjklmnpqrstvwxz]{7}/i
describe FROM_DOMAIN_NOVOWEL	From: domain has series of non-vowel letters

header FROM_LOCAL_NOVOWEL	From =~ /[bcdfghjklmnpqrstvwxz]{7}\S*\@/i
describe FROM_LOCAL_NOVOWEL	From: localpart has series of non-vowel letters

header SUBJECT_NOVOWEL		Subject =~ /[bcdfghjklmnpqrstvwxz]{8}/i
describe SUBJECT_NOVOWEL	Subject: has long non-vowel letter sequence