name : 20_head_tests.cf # SpamAssassin rules file: header tests # # Please don't modify this file as your changes will be overwritten with # the next update. Use /etc/mail/spamassassin/local.cf instead. # See 'perldoc Mail::SpamAssassin::Conf' for details. # # <@LICENSE> # Licensed to the Apache Software Foundation (ASF) under one or more # contributor license agreements. See the NOTICE file distributed with # this work for additional information regarding copyright ownership. # The ASF licenses this file to you under the Apache License, Version 2.0 # (the "License"); you may not use this file except in compliance with # the License. You may obtain a copy of the License at: # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # </@LICENSE> # ########################################################################### require_version 3.004001 ########################################################################### # partial messages; currently-theoretical attack # unsurprisingly this hits 0/0 right now. header FRAGMENTED_MESSAGE Content-Type =~ /\bmessage\/partial/i describe FRAGMENTED_MESSAGE Partial message tflags FRAGMENTED_MESSAGE userconf ########################################################################### header FROM_BLANK_NAME From =~ /(?:\s|^)"" <\S+>/i describe FROM_BLANK_NAME From: contains empty name ########################################################################### # numeric address rules, these are written to avoid overlap with each other header __FROM_ENDS_IN_NUMS From:addr =~ /\D\d{8,}\@/i header FROM_STARTS_WITH_NUMS From:addr =~ /^\d{3,50}[^0-9\@]/ describe FROM_STARTS_WITH_NUMS From: starts with several numbers # 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,})@/ ########################################################################### 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: unset@unset.unset] describe FROM_NO_USER From: has no local-part before @ sign # also 100% valid # bug 6149: avoid common .jp false positives header __PLING_QUERY Subject =~ /\?.*!|!.*\?/ meta PLING_QUERY (__PLING_QUERY && !__ISO_2022_JP_DELIM) describe PLING_QUERY Subject has exclamation mark and question mark 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) # negative lookahead exempts this MUA from circa 1997-2000 # X-Mailer: Microsoft Outlook Express 4.71.1712.3 # Message-ID: <01bd45da$2649cdc0$LocalHost@andrew> header __MSGID_DOLLARS_OK MESSAGEID =~ /<[0-9a-f]{4,}\$[0-9a-f]{4,}\$[0-9a-f]{4,}\@\S+>/ header __MSGID_DOLLARS_MAYBE MESSAGEID =~ /<\w{4,}\$\w{4,}\$(?!localhost)\w{4,}\@\S+>/i meta MSGID_DOLLARS_RANDOM __MSGID_DOLLARS_MAYBE && !__MSGID_DOLLARS_OK # bit of a ratware rule, but catches a bit more than just the one ratware header __MSGID_RANDY Message-ID =~ /<[a-z\d][a-z\d\$-]{10,29}[a-z\d]\@[a-z\d][a-z\d.]{3,12}[a-z\d]>/ # heuristic to eliminate most good Message-ID formats header __MSGID_OK_HEX Message-ID =~ /\b[a-f\d]{8}\b/ header __MSGID_OK_DIGITS Message-ID =~ /\d{10}/ header __MSGID_OK_HOST Message-ID =~ /\@(?:\D{2,}|(?:\d{1,3}\.){3}\d{1,3})>/ meta MSGID_RANDY (__MSGID_RANDY && !(__MSGID_OK_HEX || __MSGID_OK_DIGITS || __MSGID_OK_HOST)) describe MSGID_RANDY Message-Id has pattern used in spam # bug 3395 header MSGID_YAHOO_CAPS Message-ID =~ /<[A-Z]+\@yahoo.com>/ describe MSGID_YAHOO_CAPS Message-ID has ALLCAPS@yahoo.com ########################################################################### header __AT_AOL_MSGID MESSAGEID =~ /\@aol\.com\b/i header __FROM_AOL_COM From =~ /\@aol\.com\b/i meta FORGED_MSGID_AOL (__AT_AOL_MSGID && !__FROM_AOL_COM) describe FORGED_MSGID_AOL Message-ID is forged, (aol.com) header __AT_EXCITE_MSGID MESSAGEID =~ /\@excite\.com\b/i header __MY_RCVD_EXCITE Received =~ /\.excite\.com\b/i meta FORGED_MSGID_EXCITE (__AT_EXCITE_MSGID && !__MY_RCVD_EXCITE) describe FORGED_MSGID_EXCITE Message-ID is forged, (excite.com) header __AT_HOTMAIL_MSGID MESSAGEID =~ /\@hotmail\.com\b/i header __FROM_HOTMAIL_COM From =~ /\@hotmail\.com\b/i meta FORGED_MSGID_HOTMAIL (__AT_HOTMAIL_MSGID && (!__FROM_HOTMAIL_COM && !__FROM_MSN_COM && !__FROM_YAHOO_COM)) describe FORGED_MSGID_HOTMAIL Message-ID is forged, (hotmail.com) header __AT_MSN_MSGID MESSAGEID =~ /\@msn\.com\b/i header __FROM_MSN_COM From =~ /\@msn\.com\b/i meta FORGED_MSGID_MSN (__AT_MSN_MSGID && (!__FROM_MSN_COM && !__FROM_HOTMAIL_COM && !__FROM_YAHOO_COM)) describe FORGED_MSGID_MSN Message-ID is forged, (msn.com) header __AT_YAHOO_MSGID MESSAGEID =~ /\@yahoo\.com\b/i header __FROM_YAHOO_COM From =~ /\@yahoo\.com\b/i meta FORGED_MSGID_YAHOO (__AT_YAHOO_MSGID && !__FROM_YAHOO_COM) describe FORGED_MSGID_YAHOO Message-ID is forged, (yahoo.com) ########################################################################### header __MSGID_BEFORE_RECEIVED ALL =~ /^Message-Id:.*?^Received:/msi header __MSGID_BEFORE_OKAY Message-Id =~ /\@[a-z0-9.-]+\.(?:yahoo|wanadoo)(?:\.[a-z]{2,3}){1,2}>/ meta MSGID_FROM_MTA_HEADER (__MSGID_BEFORE_RECEIVED && !__MSGID_BEFORE_OKAY && !__FROM_HOTMAIL_COM) describe MSGID_FROM_MTA_HEADER Message-Id was added by a relay header MSGID_SHORT MESSAGEID =~ /^.{1,15}$|<.{0,4}\@/ describe MSGID_SHORT Message-ID is unusually short #DEMOTED TO SANDBOX - 2012-03-21 #header MSGID_MULTIPLE_AT MESSAGEID =~ /<[^>]*\@[^>]*\@/ #describe MSGID_MULTIPLE_AT Message-ID contains multiple '@' characters ########################################################################### header DATE_SPAMWARE_Y2K Date =~ /^[A-Z][a-z]{2}, \d\d [A-Z][a-z]{2} [0-6]\d \d\d:\d\d:\d\d [A-Z]{3}$/ describe DATE_SPAMWARE_Y2K Date header uses unusual Y2K formatting # as noted on the dev@ list, ":60" is valid for seconds when there's a leap # second (12/31/2005 for instance), so let's accept that as valid. ISO 8601 # apparently allows for it. # there were a few whitespace issues in the original RE, and I wanted to avoid my # two common, but yes invalid, date headers. specifically / \(GMT\)$/ and # / 0000 GMT$/. dos has / "GMT"$/ - tvd # 2.229 2.7267 0.0517 0.981 0.86 0.00 INVALID_DATE # 2.263 2.7486 0.1368 0.953 0.78 0.00 INVALID_DATE_OLD # # WRT the tests, remember that ok and fail are reversed -- so valid dates # should be "fail" and invalid dates should be "ok". header INVALID_DATE Date !~ /^\s*(?:(?i:Mon|Tue|Wed|Thu|Fri|Sat|Sun),\s)?\s*(?:[12]\d|3[01]|0?[1-9])\s+(?i:Jan|Feb|Ma[ry]|Apr|Ju[nl]|Aug|Sep|Oct|Nov|Dec)\s+(?:19[7-9]\d|2\d{3})\s+(?:[01]?\d|2[0-3])\:[0-5]\d(?::(?:[0-5]\d|60))?(?:\s+[AP]M)?(?:\s+(?:[+-][0-9]{4}|UT|[A-Z]{2,3}T|0000 GMT|"GMT"))?(?:\s*\(.*\))?\s*$/ [if-unset: Wed, 31 Jul 2002 16:41:57 +0200] describe INVALID_DATE Invalid Date: header (not RFC 2822) test INVALID_DATE fail Sat, 31 Dec 2005 23:59:60 -0500 test INVALID_DATE fail Wed, 31 Jul 2002 16:41:57 +0200 test INVALID_DATE fail Sat, 31 Dec 2005 23:00:00 test INVALID_DATE ok Sat, 31 Dec 2005 24:00:00 -0500 test INVALID_DATE ok Thurs, 31 Jul 2002 16:41:57 +0200 # allow +1300, NZ timezone header INVALID_DATE_TZ_ABSURD Date =~ /[-+](?!(?:0\d|1[0-4])(?:[03]0|[14]5))\d{4}$/ 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) ########################################################################### # MIME encoding with spam characteristics ifplugin Mail::SpamAssassin::Plugin::HeaderEval meta __SUBJECT_NEEDS_MIME __SUBJ_ILLEGAL_CHARS endif header __SUBJECT_ENCODED_QP Subject:raw =~ /=\?\S+\?Q\?/i header __SUBJECT_ENCODED_B64 Subject:raw =~ /=\?\S+\?B\?/i header __FROM_NEEDS_MIME From:name:raw =~ /[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\xff]/ header __FROM_ENCODED_QP From:raw =~ /=\?\S+\?Q\?/i header __FROM_ENCODED_B64 From:raw =~ /=\?\S+\?B\?/i meta FROM_EXCESS_BASE64 __FROM_ENCODED_B64 && !__FROM_NEEDS_MIME describe FROM_EXCESS_BASE64 From: base64 encoded unnecessarily ########################################################################### # ADV tags in various languages header ENGLISH_UCE_SUBJECT Subject =~ /^[^0-9a-z]*adv(?:ert)?\b/i describe ENGLISH_UCE_SUBJECT Subject contains an English UCE tag # alan premselaar <alien@12inch.com>, see SpamAssassin-talk list 2003-03 # quinlan: 2003-03-23 here are more generic Japanese iso-2022-jp codes # ("not yet acceptance" or "email") + "announcement" # FWIW, according to Peter Evans, this should be sufficient to catch the # UCE tag and a common attempt at evasion (using the "sue" instead of # "mi" Chinese character). 2006-10-12: updated by bug 4021. header JAPANESE_UCE_SUBJECT Subject =~ /\e\$B.*(?:L\$>5Bz|EE;R%a!<%k)(?:8x|9-)9p/ describe JAPANESE_UCE_SUBJECT Subject contains a Japanese UCE tag # check body for "shou nin daku kou koku" UCE tag (bug 4021) body __JAPANESE_UCE_BODY /(?:L\$>5Bz|EE;R%a!<%k)(?:8x|9-)9p/ meta JAPANESE_UCE_BODY (__ISO_2022_JP_DELIM && __JAPANESE_UCE_BODY) describe JAPANESE_UCE_BODY Body contains Japanese UCE tag # quinlan: "advertisement" in Russian KOI8-R # (no longer common, but worth noting in future) #header RUSSIAN_UCE_SUBJECT Subject =~ /\xf0\xe5\xea\xeb\xe0\xec\xf3/ #describe RUSSIAN_UCE_SUBJECT Subject contains a Russian UCE tag # Korean UCE Subject: lines are usually 8-bit, but are occasionally encoded # with quoted-printable or base64. # # \xbc\xba\xc0\xce means "adult" # \xb1\xa4\xb0\xed means "advertisement" # \xc1\xa4\xba\xb8 means "information" # \xc8\xab\xba\xb8 means "publicity" # # Each two byte sequence is one Korean letter; the spaces and periods are # sometimes used to obscure the words. \xb1\xa4\xb0\xed is the most common # tag and is sometimes very obscured so we look harder. # header KOREAN_UCE_SUBJECT Subject =~ /[({[<][. ]*(?-i:\xbc\xba[. ]*\xc0\xce[. ]*)?(?-i:\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 ########################################################################### # two reliable signatures header __DOUBLE_IP_SPAM_1 Received =~ /from \[\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\] by \d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3} with/ header __DOUBLE_IP_SPAM_2 Received =~ /from\s+\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\s+by\s+\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3};/ # loose match header __DOUBLE_IP_LOOSE Received =~ /(?:\b(?:from|by)\b.{1,4}\b\d{1,3}[._-]\d{1,3}[._-]\d{1,3}[._-]\d{1,3}(?<!127\.0\.0\.1)\b.{0,4}){2}/i # spam signature meta RCVD_DOUBLE_IP_SPAM (__DOUBLE_IP_SPAM_1 || __DOUBLE_IP_SPAM_2) describe RCVD_DOUBLE_IP_SPAM Bulk email fingerprint (double IP) found # other matches meta RCVD_DOUBLE_IP_LOOSE (__DOUBLE_IP_LOOSE && !RCVD_DOUBLE_IP_SPAM) describe RCVD_DOUBLE_IP_LOOSE Received: by and from look like IP addresses 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 # forgery meta-rules: more reliable than their inputs meta CONFIRMED_FORGED (__FORGED_RCVD_TRAIL && (__FORGED_AOL_RCVD || __FORGED_HOTMAIL_RCVD || __FORGED_EUDORAMAIL_RCVD || FORGED_YAHOO_RCVD || __FORGED_JUNO_RCVD || FORGED_GMAIL_RCVD)) describe CONFIRMED_FORGED Received headers are forged meta MULTI_FORGED ((__FORGED_AOL_RCVD + __FORGED_HOTMAIL_RCVD + __FORGED_EUDORAMAIL_RCVD + FORGED_YAHOO_RCVD + __FORGED_JUNO_RCVD + FORGED_GMAIL_RCVD) > 1) describe MULTI_FORGED Received headers indicate multiple forgeries header NONEXISTENT_CHARSET Content-Type =~ /charset=.?DEFAULT/ describe NONEXISTENT_CHARSET Character set doesn't exist header __HAS_MESSAGE_ID exists:Message-Id meta MISSING_MID !__HAS_MESSAGE_ID describe MISSING_MID Missing Message-Id: header header __HAS_DATE exists:Date meta MISSING_DATE !__HAS_DATE describe MISSING_DATE Missing Date: header header __HAS_SUBJECT exists:Subject meta MISSING_SUBJECT !__HAS_SUBJECT describe MISSING_SUBJECT Missing Subject: header # bug 6353 header __HAS_FROM exists:From meta MISSING_FROM !__HAS_FROM describe MISSING_FROM Missing From: header # bug 6149: avoid common .jp false positives header __GAPPY_SUBJECT Subject =~ /\b(?:[a-z]([-_. =~\/:,*!\@\#\$\%\^&+;\"\'<>\\])\1{0,2}){4}/i meta GAPPY_SUBJECT (__GAPPY_SUBJECT && !__ISO_2022_JP_DELIM) describe GAPPY_SUBJECT Subject: contains G.a.p.p.y-T.e.x.t ### header existence tests (description is added automatically) # X-Fix example: NTMail fixed non RFC822 compliant EMail message # # X-PMFLAGS is all caps # # Headers that seem to only be used by a single spamming software and # are found together in the same message: # 1. X-MailingID and X-ServerHost # 2. X-Stormpost-To and X-List-Unsubscribe # # not spammish: X-EM-Registration, X-EM-Version, X-Antiabuse, X-List-Host, # X-Message-Id # bad FP rate: Comment, Date-warning 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 __HAS_MIMEOLE exists:X-MimeOLE header __HAS_MSMAIL_PRI exists:X-MSMail-Priority header __HAS_SQUIRRELMAIL_IN_MAILER X-Mailer =~ /SquirrelMail\b/ # Ever growing Office version list without X-MimeOLE, bug 6346, 7122, 7463. header __HAS_OFFICE1214_IN_MAILER X-Mailer =~ /^Microsoft (?:Office )?Outlook 1[2456]\.0/ meta MISSING_MIMEOLE (__HAS_MSMAIL_PRI && !__HAS_MIMEOLE && !__HAS_SQUIRRELMAIL_IN_MAILER && !__HAS_OFFICE1214_IN_MAILER) describe MISSING_MIMEOLE Message has X-MSMail-Priority, but no X-MimeOLE header __HAS_X_MAILER exists:X-Mailer header __IS_EXCH X-MimeOLE =~ /Produced By Microsoft Exchange V/ 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 #DISABLING DUE TO POOR S/O 2012-09-27 #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" # the real services never HELO as 'foo.com', instead 'mail.foo.com' or # something like that. Note: be careful when expanding this... legit dotcom # HELOers include: hotmail.com, drizzle.com, lockergnome.com. 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 # MIME boundary tests; spam tools use distinctive patterns. header MIME_BOUND_DD_DIGITS Content-Type =~ /boundary=\"--\d+\"/ describe MIME_BOUND_DD_DIGITS 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 # 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: unset@unset.unset] describe TO_MALFORMED To: has a malformed address header __CD exists:Content-Disposition header __CT exists:Content-Type header __CTE exists:Content-Transfer-Encoding header __MIME_VERSION exists:MIME-Version header __CT_TEXT_PLAIN Content-Type =~ /^text\/plain\b/i meta MIME_HEADER_CTYPE_ONLY (!__CD && !__CTE && __CT && !__MIME_VERSION && !__CT_TEXT_PLAIN) describe MIME_HEADER_CTYPE_ONLY 'Content-Type' found without required MIME headers header WITH_LC_SMTP Received =~ /\swith\ssmtp;\s/ describe WITH_LC_SMTP Received line contains spam-sign (lowercase smtp) 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 __USER_AGENT_MSN X-Mailer =~ /^MSN Explorer / # 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' # thanks to David Ritz for passing this on header UNCLOSED_BRACKET ALL =~ /\[\d+\r?\n/s describe UNCLOSED_BRACKET Headers contain an unclosed bracket header FROM_DOMAIN_NOVOWEL From =~ /\@\S*[bcdfgjklmnpqrstvwxz]{7}/i describe FROM_DOMAIN_NOVOWEL From: domain has series of non-vowel letters tflags FROM_DOMAIN_NOVOWEL userconf # lock scores low header FROM_LOCAL_NOVOWEL From =~ /[bcdfgjklmnpqrstvwxz]{7}\S*\@/i describe FROM_LOCAL_NOVOWEL From: localpart has series of non-vowel letters tflags FROM_LOCAL_NOVOWEL userconf # lock scores low header FROM_LOCAL_HEX From =~ /[0-9a-f]{11}\S*\@/i describe FROM_LOCAL_HEX From: localpart has long hexadecimal sequence header FROM_LOCAL_DIGITS From =~ /\d{11}\S*\@/i describe FROM_LOCAL_DIGITS From: localpart has long digit sequence header __TOCC_EXISTS exists:ToCc header X_PRIORITY_CC ALL =~ /^X-Priority:[^\n]{0,80}^Cc:/msi describe X_PRIORITY_CC Cc: after X-Priority: (bulk email fingerprint) # catch non-RFC2047 compliant messages # Apple Mail has a bug where headers will have whitespace around the encoded # text, so try to ignore that header BAD_ENC_HEADER ALL:raw =~ /=\?[^?\s]+\?[^?\s]\?\s*[^?]+\s(?!\?=)/ describe BAD_ENC_HEADER Message has bad MIME encoding in the header header __ML1 Precedence =~ m{\b(list|bulk)\b}i header __ML2 exists:List-Id header __ML3 exists:List-Post header __ML4 exists:Mailing-List header __ML5 Return-Path:addr =~ m{^([^\@]+-(request|bounces|admin|owner)|owner-[^\@]+)(\@|\z)}i meta __VIA_ML __ML1 || __ML2 || __ML3 || __ML4 || __ML5 describe __VIA_ML Mail from a mailing list # some clueless mailing lists (like zmailer with an RFC822TABS option on) # are replacing a leading space by a TAB in header fields From, To, # Cc, Date (Bug 6429) header __ML_TURNS_SP_TO_TAB Received =~ /\(ORCPT <rfc822;/ describe __ML_TURNS_SP_TO_TAB A mailing list changing a space to a TAB # must keep it in sync with http://www.iana.org/assignments/ipv4-address-space/ header RCVD_ILLEGAL_IP X-Spam-Relays-Untrusted =~ / (?:by|ip)=(?=\d+\.\d+\.\d+\.\d+ )(?:(?:0|2(?:2[4-9]|[3-5]\d)|192\.0\.2|198\.51\.100|203\.0\.113)\.|(?:\d+\.){0,3}(?!(?:2(?:[0-4]\d|5[0-5])|[01]?\d\d?)\b))/ describe RCVD_ILLEGAL_IP Received: contains illegal IP address ########################################################################### ifplugin Mail::SpamAssassin::Plugin::HeaderEval header __FORGED_AOL_RCVD eval:check_for_fake_aol_relay_in_rcvd() header CHARSET_FARAWAY_HEADER eval:check_for_faraway_charset_in_headers() describe CHARSET_FARAWAY_HEADER A foreign language charset used in headers tflags CHARSET_FARAWAY_HEADER userconf ################################################################### # illegal characters that should be MIME encoded # might want to exempt users using languages that don't use Latin # alphabets, but do it in the eval header __SUBJ_ILLEGAL_CHARS eval:check_illegal_chars('Subject','0.00','2') meta SUBJ_ILLEGAL_CHARS (__SUBJ_ILLEGAL_CHARS && !__FROM_YAHOO_COM) describe SUBJ_ILLEGAL_CHARS Subject: has too many raw illegal characters header FROM_ILLEGAL_CHARS eval:check_illegal_chars('From','0.20','2') describe FROM_ILLEGAL_CHARS From: has too many raw illegal characters header __HEAD_ILLEGAL_CHARS eval:check_illegal_chars('ALL','0.010','2') meta HEAD_ILLEGAL_CHARS __HEAD_ILLEGAL_CHARS && !__SUBJ_ILLEGAL_CHARS && !FROM_ILLEGAL_CHARS describe HEAD_ILLEGAL_CHARS Headers have too many raw illegal characters ################################################################### # a forged Hotmail message; host HELO'd as hotmail.com, but it wasn't header __FORGED_HOTMAIL_RCVD eval:check_for_forged_hotmail_received_headers() # 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() header FORGED_YAHOO_RCVD eval:check_for_forged_yahoo_received_headers() describe FORGED_YAHOO_RCVD 'From' yahoo.com does not match 'Received' headers if (version >= 3.004002) header FORGED_GMAIL_RCVD eval:check_for_forged_gmail_received_headers() describe FORGED_GMAIL_RCVD 'From' gmail.com does not match 'Received' headers endif header __FORGED_JUNO_RCVD eval:check_for_forged_juno_received_headers() header SORTED_RECIPS eval:sorted_recipients() describe SORTED_RECIPS Recipient list is sorted by address header SUSPICIOUS_RECIPS eval:similar_recipients('0.65','undef') describe SUSPICIOUS_RECIPS Similar addresses in recipient list # this is a quite common false positive, as it's legal to remove a To but leave # a CC. so don't score it high. header MISSING_HEADERS eval:check_for_missing_to_header() describe MISSING_HEADERS Missing To: header header DATE_IN_PAST_03_06 eval:check_for_shifted_date('-6', '-3') describe DATE_IN_PAST_03_06 Date: is 3 to 6 hours before Received: date header DATE_IN_PAST_06_12 eval:check_for_shifted_date('-12', '-6') describe DATE_IN_PAST_06_12 Date: is 6 to 12 hours before Received: date header DATE_IN_PAST_12_24 eval:check_for_shifted_date('-24', '-12') describe DATE_IN_PAST_12_24 Date: is 12 to 24 hours before Received: date header DATE_IN_PAST_24_48 eval:check_for_shifted_date('-48', '-24') describe DATE_IN_PAST_24_48 Date: is 24 to 48 hours before Received: date header DATE_IN_PAST_96_XX eval:check_for_shifted_date('undef', '-96') describe DATE_IN_PAST_96_XX Date: is 96 hours or more before Received: date header DATE_IN_FUTURE_03_06 eval:check_for_shifted_date('3', '6') describe DATE_IN_FUTURE_03_06 Date: is 3 to 6 hours after Received: date header DATE_IN_FUTURE_06_12 eval:check_for_shifted_date('6', '12') describe DATE_IN_FUTURE_06_12 Date: is 6 to 12 hours after Received: date header DATE_IN_FUTURE_12_24 eval:check_for_shifted_date('12', '24') describe DATE_IN_FUTURE_12_24 Date: is 12 to 24 hours after Received: date header DATE_IN_FUTURE_24_48 eval:check_for_shifted_date('24', '48') describe DATE_IN_FUTURE_24_48 Date: is 24 to 48 hours after Received: date header DATE_IN_FUTURE_48_96 eval:check_for_shifted_date('48', '96') describe DATE_IN_FUTURE_48_96 Date: is 48 to 96 hours after Received: date #header DATE_IN_FUTURE_96_XX eval:check_for_shifted_date('96', 'undef') meta DATE_IN_FUTURE_96_XX (0) describe DATE_IN_FUTURE_96_XX Date: is 96 hours or more after Received: date header UNRESOLVED_TEMPLATE eval:check_unresolved_template() describe UNRESOLVED_TEMPLATE Headers contain an unresolved template header SUBJ_ALL_CAPS eval:subject_is_all_caps() describe SUBJ_ALL_CAPS Subject is all capitals header LOCALPART_IN_SUBJECT eval:check_for_to_in_subject('user') describe LOCALPART_IN_SUBJECT Local part of To: address appears in Subject header MSGID_OUTLOOK_INVALID eval:check_outlook_message_id() describe MSGID_OUTLOOK_INVALID Message-Id is fake (in Outlook Express format) header HEADER_COUNT_CTYPE eval:check_header_count_range('Content-Type','2','999') describe HEADER_COUNT_CTYPE Multiple Content-Type headers found endif ########################################################################### ifplugin Mail::SpamAssassin::Plugin::MIMEEval # this is also mostly-theoretical, so allow 0 hits header HEAD_LONG eval:check_msg_parse_flags('truncated_header') describe HEAD_LONG Message headers are very long tflags HEAD_LONG userconf header MISSING_HB_SEP eval:check_msg_parse_flags('missing_head_body_separator') describe MISSING_HB_SEP Missing blank line between message header and body tflags MISSING_HB_SEP userconf endif ########################################################################### ifplugin Mail::SpamAssassin::Plugin::RelayEval header __UNPARSEABLE_RELAY_COUNT eval:check_relays_unparseable() tflags __UNPARSEABLE_RELAY_COUNT userconf meta UNPARSEABLE_RELAY (__UNPARSEABLE_RELAY_COUNT >= 1) tflags UNPARSEABLE_RELAY userconf describe UNPARSEABLE_RELAY Informational: message has unparseable relay lines header RCVD_HELO_IP_MISMATCH eval:helo_ip_mismatch() describe RCVD_HELO_IP_MISMATCH Received: HELO and IP do not match, but should # not used directly right now due to FPs; but CONFIRMED_FORGED turns it # into a 1.0 S/O rule anyway, so that's not a problem ;) # 2.626 3.6340 1.5251 0.704 0.34 1.44 FORGED_RCVD_TRAIL # 0.956 3.3890 0.0000 1.000 0.98 4.30 CONFIRMED_FORGED header __FORGED_RCVD_TRAIL eval:check_for_forged_received_trail() header NO_RDNS_DOTCOM_HELO eval:check_for_no_rdns_dotcom_helo() describe NO_RDNS_DOTCOM_HELO Host HELO'd as a big ISP, but had no rDNS endif ifplugin Mail::SpamAssassin::Plugin::HeaderEval header __ENV_AND_HDR_FROM_MATCH eval:check_for_matching_env_and_hdr_from() endif