/usr/share/perl5/Mail/SpamAssassin/Plugin/HeaderEval.pm is in spamassassin 3.4.0-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 | # <@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>
package Mail::SpamAssassin::Plugin::HeaderEval;
use strict;
use warnings;
use bytes;
use re 'taint';
use Errno qw(EBADF);
use Mail::SpamAssassin::Plugin;
use Mail::SpamAssassin::Locales;
use Mail::SpamAssassin::Logger;
use Mail::SpamAssassin::Constants qw(:sa :ip);
use vars qw(@ISA);
@ISA = qw(Mail::SpamAssassin::Plugin);
# constructor: register the eval rule
sub new {
my $class = shift;
my $mailsaobject = shift;
# some boilerplate...
$class = ref($class) || $class;
my $self = $class->SUPER::new($mailsaobject);
bless ($self, $class);
# the important bit!
$self->register_eval_rule("check_for_fake_aol_relay_in_rcvd");
$self->register_eval_rule("check_for_faraway_charset_in_headers");
$self->register_eval_rule("check_for_unique_subject_id");
$self->register_eval_rule("check_illegal_chars");
$self->register_eval_rule("check_for_forged_hotmail_received_headers");
$self->register_eval_rule("check_for_no_hotmail_received_headers");
$self->register_eval_rule("check_for_msn_groups_headers");
$self->register_eval_rule("check_for_forged_eudoramail_received_headers");
$self->register_eval_rule("check_for_forged_yahoo_received_headers");
$self->register_eval_rule("check_for_forged_juno_received_headers");
$self->register_eval_rule("check_for_matching_env_and_hdr_from");
$self->register_eval_rule("sorted_recipients");
$self->register_eval_rule("similar_recipients");
$self->register_eval_rule("check_for_missing_to_header");
$self->register_eval_rule("check_for_forged_gw05_received_headers");
$self->register_eval_rule("check_for_shifted_date");
$self->register_eval_rule("subject_is_all_caps");
$self->register_eval_rule("check_for_to_in_subject");
$self->register_eval_rule("check_outlook_message_id");
$self->register_eval_rule("check_messageid_not_usable");
$self->register_eval_rule("check_header_count_range");
$self->register_eval_rule("check_unresolved_template");
$self->register_eval_rule("check_ratware_name_id");
$self->register_eval_rule("check_ratware_envelope_from");
$self->register_eval_rule("gated_through_received_hdr_remover");
$self->register_eval_rule("received_within_months");
$self->register_eval_rule("check_equal_from_domains");
return $self;
}
# load triplets.txt into memory
sub compile_now_start {
my ($self) = @_;
$self->word_is_in_dictionary("aba");
}
sub check_for_fake_aol_relay_in_rcvd {
my ($self, $pms) = @_;
local ($_);
$_ = $pms->get('Received');
s/\s/ /gs;
# this is the hostname format used by AOL for their relays. Spammers love
# forging it. Don't make it more specific to match aol.com only, though --
# there's another set of spammers who generate fake hostnames to go with
# it!
if (/ rly-[a-z][a-z]\d\d\./i) {
return 0 if /\/AOL-\d+\.\d+\.\d+\)/; # via AOL mail relay
return 0 if /ESMTP id (?:RELAY|MAILRELAY|MAILIN)/; # AOLish
return 1;
}
# spam: Received: from unknown (HELO mta05bw.bigpond.com) (80.71.176.130) by
# rly-xw01.mx.aol.com with QMQP; Sat, 15 Jun 2002 23:37:16 -0000
# non: Received: from rly-xj02.mx.aol.com (rly-xj02.mail.aol.com [172.20.116.39]) by
# omr-r05.mx.aol.com (v83.35) with ESMTP id RELAYIN7-0501132011; Wed, 01
# May 2002 13:20:11 -0400
# non: Received: from logs-tr.proxy.aol.com (logs-tr.proxy.aol.com [152.163.201.132])
# by rly-ip01.mx.aol.com (8.8.8/8.8.8/AOL-5.0.0)
# with ESMTP id NAA08955 for <sapient-alumni@yahoogroups.com>;
# Thu, 4 Apr 2002 13:11:20 -0500 (EST)
return 0;
}
sub check_for_faraway_charset_in_headers {
my ($self, $pms) = @_;
my $hdr;
my @locales = Mail::SpamAssassin::Util::get_my_locales($self->{main}->{conf}->{ok_locales});
return 0 if grep { $_ eq "all" } @locales;
for my $h (qw(From Subject)) {
my @hdrs = $pms->get("$h:raw"); # ??? get() returns a scalar ???
if ($#hdrs >= 0) {
$hdr = join(" ", @hdrs);
} else {
$hdr = '';
}
while ($hdr =~ /=\?(.+?)\?.\?.*?\?=/g) {
Mail::SpamAssassin::Locales::is_charset_ok_for_locales($1, @locales)
or return 1;
}
}
0;
}
sub check_for_unique_subject_id {
my ($self, $pms) = @_;
local ($_);
$_ = lc $pms->get('Subject');
study; # study is a no-op since perl 5.16.0, eliminating related bugs
my $id = 0;
if (/[-_\.\s]{7,}([-a-z0-9]{4,})$/
|| /\s{10,}(?:\S\s)?(\S+)$/
|| /\s{3,}[-:\#\(\[]+([-a-z0-9]{4,})[\]\)]+$/
|| /\s{3,}[:\#\(\[]*([a-f0-9]{4,})[\]\)]*$/
|| /\s{3,}[-:\#]([a-z0-9]{5,})$/
|| /[\s._]{3,}([^0\s._]\d{3,})$/
|| /[\s._]{3,}\[(\S+)\]$/
# (7217vPhZ0-478TLdy5829qicU9-0@26) and similar
|| /\(([-\w]{7,}\@\d+)\)$/
# Seven or more digits at the end of a subject is almost certainly a id
|| /\b(\d{7,})\s*$/
# stuff at end of line after "!" or "?" is usually an id
|| /[!\?]\s*(\d{4,}|\w+(-\w+)+)\s*$/
# 9095IPZK7-095wsvp8715rJgY8-286-28 and similar
# excluding 'Re:', etc and the first word
|| /(?:\w{2,3}:\s)?\w+\s+(\w{7,}-\w{7,}(-\w+)*)\s*$/
# #30D7 and similar
|| /\s#\s*([a-f0-9]{4,})\s*$/
)
{
$id = $1;
# exempt online purchases
if ($id =~ /\d{5,}/
&& /(?:item|invoice|order|number|confirmation).{1,6}\Q$id\E\s*$/)
{
$id = 0;
}
# for the "foo-bar-baz" case, otherwise it won't
# be found in the dict:
$id =~ s/-//;
}
return ($id && !$self->word_is_in_dictionary($id));
}
# word_is_in_dictionary()
#
# See if the word looks like an English word, by checking if each triplet
# of letters it contains is one that can be found in the English language.
# Does not include triplets only found in proper names, or in the Latin
# and Greek terms that might be found in a larger dictionary
my %triplets;
my $triplets_loaded = 0;
sub word_is_in_dictionary {
my ($self, $word) = @_;
local ($_);
local $/ = "\n"; # Ensure $/ is set appropriately
# $word =~ tr/A-Z/a-z/; # already done by this stage
$word =~ s/^\s+//;
$word =~ s/\s+$//;
# If it contains a digit, dash, etc, it's not a valid word.
# Don't reject words like "can't" and "I'll"
return 0 if ($word =~ /[^a-z\']/);
# handle a few common "blah blah blah (comment)" styles
return 1 if ($word eq "ot"); # off-topic
return 1 if ($word =~ /(?:linux|nix|bsd)/); # not in most dicts
return 1 if ($word =~ /(?:whew|phew|attn|tha?nx)/); # not in most dicts
my $word_len = length($word);
# Unique IDs probably aren't going to be only one or two letters long
return 1 if ($word_len < 3);
if (!$triplets_loaded) {
# take a copy to avoid modifying the real one
my @default_triplets_path = @Mail::SpamAssassin::default_rules_path;
s{$}{/triplets.txt} for @default_triplets_path;
my $filename = $self->{main}->first_existing_path (@default_triplets_path);
if (!defined $filename) {
dbg("eval: failed to locate the triplets.txt file");
return 1;
}
local *TRIPLETS;
if (!open (TRIPLETS, "<$filename")) {
dbg("eval: failed to open '$filename', cannot check dictionary: $!");
return 1;
}
for($!=0; <TRIPLETS>; $!=0) {
chomp;
$triplets{$_} = 1;
}
defined $_ || $!==0 or
$!==EBADF ? dbg("eval: error reading from $filename: $!")
: die "error reading from $filename: $!";
close(TRIPLETS) or die "error closing $filename: $!";
$triplets_loaded = 1;
} # if (!$triplets_loaded)
my $i;
for ($i = 0; $i < ($word_len - 2); $i++) {
my $triplet = substr($word, $i, 3);
if (!$triplets{$triplet}) {
dbg("eval: unique ID: letter triplet '$triplet' from word '$word' not valid");
return 0;
}
} # for ($i = 0; $i < ($word_len - 2); $i++)
# All letter triplets in word were found to be valid
return 1;
}
# look for 8-bit and other illegal characters that should be MIME
# encoded, these might want to exempt languages that do not use
# Latin-based alphabets, but only if the user wants it that way
sub check_illegal_chars {
my ($self, $pms, $header, $ratio, $count) = @_;
$header .= ":raw" unless ($header eq "ALL" || $header =~ /:raw$/);
my $str = $pms->get($header);
return 0 unless $str ne '';
# avoid overlap between tests
if ($header eq "ALL") {
# fix continuation lines, then remove Subject and From
$str =~ s/\n[ \t]+/ /gs;
$str =~ s/^(?:Subject|From):.*$//gm;
}
# count illegal substrings (RFC 2045)
my $illegal = () = ($str =~ /[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\xff]/g);
# minor exemptions for Subject
if ($header eq "Subject:raw") {
# only exempt a single cent sign, pound sign, or registered sign
my $exempt = () = ($str =~ /[\xa2\xa3\xae]/g);
$illegal-- if $exempt == 1;
}
return 0 if (length($str) == 0);
return (($illegal / length($str)) >= $ratio && $illegal >= $count);
}
# ezmlm has a very bad habit of removing Received: headers! bad ezmlm.
#
sub gated_through_received_hdr_remover {
my ($self, $pms) = @_;
my $txt = $pms->get("Mailing-List",undef);
if (defined $txt && $txt =~ /^contact \S+\@\S+\; run by ezmlm$/) {
my $dlto = $pms->get("Delivered-To");
my $rcvd = $pms->get("Received");
# ensure we have other indicative headers too
if ($dlto =~ /^mailing list \S+\@\S+/ &&
$rcvd =~ /qmail \d+ invoked (?:from network|by .{3,20})\); \d+ ... \d+/)
{
return 1;
}
}
my $rcvd = $pms->get("Received",undef);
if (!defined $rcvd) {
# we have no Received headers! These tests cannot run in that case
return 1;
}
# MSN groups removes Received lines. thanks MSN
if ($rcvd =~ /from groups\.msn\.com \(\S+\.msn\.com /) {
return 1;
}
return 0;
}
# FORGED_HOTMAIL_RCVD
sub _check_for_forged_hotmail_received_headers {
my ($self, $pms) = @_;
if (defined $pms->{hotmail_addr_but_no_hotmail_received}) { return; }
$pms->{hotmail_addr_with_forged_hotmail_received} = 0;
$pms->{hotmail_addr_but_no_hotmail_received} = 0;
my $rcvd = $pms->get('Received');
$rcvd =~ s/\s+/ /gs; # just spaces, simplify the regexp
return if ($rcvd =~
/from mail pickup service by hotmail\.com with Microsoft SMTPSVC;/);
# Microsoft passes Hotmail mail directly to MSN Group servers.
return if $self->check_for_msn_groups_headers($pms);
my $ip = $pms->get('X-Originating-Ip',undef);
my $IP_ADDRESS = IP_ADDRESS;
if (defined $ip && $ip =~ /$IP_ADDRESS/) { $ip = 1; } else { $ip = 0; }
# Hotmail formats its received headers like this:
# Received: from hotmail.com (f135.law8.hotmail.com [216.33.241.135])
# spammers do not ;)
if ($self->gated_through_received_hdr_remover($pms)) { return; }
if ($rcvd =~ /from (?:\S*\.)?hotmail.com \(\S+\.hotmail(?:\.msn)?\.com[ \)]/ && $ip)
{ return; }
if ($rcvd =~ /from \S*\.hotmail.com \(\[$IP_ADDRESS\][ \):]/ && $ip)
{ return; }
if ($rcvd =~ /from \S+ by \S+\.hotmail(?:\.msn)?\.com with HTTP\;/ && $ip)
{ return; }
if ($rcvd =~ /from \[66\.218.\S+\] by \S+\.yahoo\.com/ && $ip)
{ return; }
if ($rcvd =~ /(?:from |HELO |helo=)\S*hotmail\.com\b/) {
# HELO'd as hotmail.com, despite not being hotmail
$pms->{hotmail_addr_with_forged_hotmail_received} = 1;
} else {
# check to see if From claimed to be @hotmail.com
my $from = $pms->get('From:addr');
if ($from !~ /\bhotmail\.com$/i) { return; }
$pms->{hotmail_addr_but_no_hotmail_received} = 1;
}
}
# FORGED_HOTMAIL_RCVD
sub check_for_forged_hotmail_received_headers {
my ($self, $pms) = @_;
$self->_check_for_forged_hotmail_received_headers($pms);
return $pms->{hotmail_addr_with_forged_hotmail_received};
}
# SEMIFORGED_HOTMAIL_RCVD
sub check_for_no_hotmail_received_headers {
my ($self, $pms) = @_;
$self->_check_for_forged_hotmail_received_headers($pms);
return $pms->{hotmail_addr_but_no_hotmail_received};
}
# MSN_GROUPS
sub check_for_msn_groups_headers {
my ($self, $pms) = @_;
my $to = $pms->get('To');
return 0 unless $to =~ /<(\S+)\@groups\.msn\.com>/i;
my $listname = $1;
# from Theo Van Dinter, see bug 591
# Updated by DOS, based on messages from Bob Menschel, bug 4301
return 0 unless $pms->get('Received') =~
/from mail pickup service by ((?:p\d\d\.)groups\.msn\.com)\b/;
my $server = $1;
if ($listname =~ /^notifications$/) {
return 0 unless $pms->get('Message-Id') =~ /^<\S+\@$server>/;
} else {
return 0 unless $pms->get('Message-Id') =~ /^<$listname-\S+\@groups\.msn\.com>/;
return 0 unless $pms->get('EnvelopeFrom:addr') =~ /$listname-bounce\@groups\.msn\.com/;
}
return 1;
# MSN Groups
# Return-path: <ListName-bounce@groups.msn.com>
# Received: from groups.msn.com (tk2dcpuba02.msn.com [65.54.195.210]) by
# dogma.slashnull.org (8.11.6/8.11.6) with ESMTP id g72K35v10457 for
# <zzzzzzzzzzzz@jmason.org>; Fri, 2 Aug 2002 21:03:05 +0100
# Received: from mail pickup service by groups.msn.com with Microsoft
# SMTPSVC; Fri, 2 Aug 2002 13:01:30 -0700
# Message-id: <ListName-1392@groups.msn.com>
# X-loop: notifications@groups.msn.com
# Reply-to: "List Full Name" <ListName@groups.msn.com>
# To: "List Full Name" <ListName@groups.msn.com>
# Return-path: <ListName-bounce@groups.msn.com>
# Received: from p04.groups.msn.com ([65.54.195.216]) etc...
# Received: from mail pickup service by p04.groups.msn.com with Microsoft SMTPSVC;
# Thu, 5 May 2005 20:30:37 -0700
# X-Originating-Ip: 207.68.170.30
# From: =?iso-8859-1?B?IqSj4/D9pEbzeN9s9vLw6qQiIA==?=<zzzzzzzz@hotmail.com>
# To: "Managers of List Name" <notifications@groups.msn.com>
# Subject: =?iso-8859-1?Q?APPROVAL_NEEDED:_=A4=A3=E3=F0=FD=A4F=F3x=DFl?=
# =?iso-8859-1?Q?=F6=F2=F0=EA=A4_applied_to_join_List_Name=2C?=
# =?iso-8859-1?Q?_an_MSN_Group?=
# Date: Thu, 5 May 2005 20:30:37 -0700
# MIME-Version: 1.0
# Content-Type: multipart/alternative;
# boundary="----=_NextPart_000_333944_01C551B1.4BBA02B0"
# X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4927.1200
# Message-ID: <TK2DCPUBA042cv0aGlt00020aa3@p04.groups.msn.com>
# Return-path: <ListName-bounce@groups.msn.com>
# Received: from [65.54.208.83] (helo=p05.groups.msn.com) etc...
# Received: from mail pickup service by p05.groups.msn.com with Microsoft SMTPSVC;
# Fri, 6 May 2005 14:59:25 -0700
# X-Originating-Ip: 207.68.170.30
# Message-Id: <ListName-101@groups.msn.com>
# Reply-To: "List Name" <ListName@groups.msn.com>
# From: "whoever" <zzzzzzzzzz@hotmail.com>
# To: "List Name" <ListName@groups.msn.com>
# Subject: whatever
# Date: Fri, 6 May 2005 14:59:25 -0700
}
###########################################################################
sub check_for_forged_eudoramail_received_headers {
my ($self, $pms) = @_;
my $from = $pms->get('From:addr');
if ($from !~ /\beudoramail\.com$/i) { return 0; }
my $rcvd = $pms->get('Received');
$rcvd =~ s/\s+/ /gs; # just spaces, simplify the regexp
my $ip = $pms->get('X-Sender-Ip',undef);
my $IP_ADDRESS = IP_ADDRESS;
if (defined $ip && $ip =~ /$IP_ADDRESS/) { $ip = 1; } else { $ip = 0; }
# Eudoramail formats its received headers like this:
# Received: from Unknown/Local ([?.?.?.?]) by shared1-mail.whowhere.com;
# Thu Nov 29 13:44:25 2001
# Message-Id: <JGDHDEHPPJECDAAA@shared1-mail.whowhere.com>
# Organization: QUALCOMM Eudora Web-Mail (http://www.eudoramail.com:80)
# X-Sender-Ip: 192.175.21.146
# X-Mailer: MailCity Service
if ($self->gated_through_received_hdr_remover($pms)) { return 0; }
if ($rcvd =~ /by \S*whowhere.com\;/ && $ip) { return 0; }
return 1;
}
###########################################################################
sub check_for_forged_yahoo_received_headers {
my ($self, $pms) = @_;
my $from = $pms->get('From:addr');
if ($from !~ /\byahoo\.com$/i) { return 0; }
my $rcvd = $pms->get('Received');
if ($pms->get("Resent-From") ne '' && $pms->get("Resent-To") ne '') {
my $xrcvd = $pms->get("X-Received");
$rcvd = $xrcvd if $xrcvd ne '';
}
$rcvd =~ s/\s+/ /gs; # just spaces, simplify the regexp
# not sure about this
#if ($rcvd !~ /from \S*yahoo\.com/) { return 0; }
if ($self->gated_through_received_hdr_remover($pms)) { return 0; }
# bug 3740: ignore bounces from Yahoo!. only honoured if the
# correct rDNS shows up in the trusted relay list, or first untrusted relay
#
# bug 4528: [ ip=68.142.202.54 rdns=mta122.mail.mud.yahoo.com
# helo=mta122.mail.mud.yahoo.com by=eclectic.kluge.net ident=
# envfrom= intl=0 id=49F2EAF13B auth= ]
#
if ($pms->{relays_trusted_str} =~ / rdns=\S+\.yahoo\.com /
|| $pms->{relays_untrusted_str} =~ /^[^\]]+ rdns=\S+\.yahoo\.com /)
{ return 0; }
if ($rcvd =~ /by web\S+\.mail\S*\.yahoo\.com via HTTP/) { return 0; }
if ($rcvd =~ /by smtp\S+\.yahoo\.com with SMTP/) { return 0; }
my $IP_ADDRESS = IP_ADDRESS;
if ($rcvd =~
/from \[$IP_ADDRESS\] by \S+\.(?:groups|scd|dcn)\.yahoo\.com with NNFMP/) {
return 0;
}
# used in "forward this news item to a friend" links. There's no better
# received hdrs to match on, unfortunately. I'm not sure if the next test is
# still useful, as a result.
#
# search for msgid <20020929140301.451A92940A9@xent.com>, subject "Yahoo!
# News Story - Top Stories", date Sep 29 2002 on
# <http://xent.com/pipermail/fork/> for an example.
#
if ($rcvd =~ /\bmailer\d+\.bulk\.scd\.yahoo\.com\b/
&& $from =~ /\@reply\.yahoo\.com$/i) { return 0; }
if ($rcvd =~ /by \w+\.\w+\.yahoo\.com \(\d+\.\d+\.\d+\/\d+\.\d+\.\d+\)(?: with ESMTP)? id \w+/) {
# possibly sent from "mail this story to a friend"
return 0;
}
return 1;
}
sub check_for_forged_juno_received_headers {
my ($self, $pms) = @_;
my $from = $pms->get('From:addr');
if ($from !~ /\bjuno\.com$/i) { return 0; }
if ($self->gated_through_received_hdr_remover($pms)) { return 0; }
my $xorig = $pms->get('X-Originating-IP');
my $xmailer = $pms->get('X-Mailer');
my $rcvd = $pms->get('Received');
my $IP_ADDRESS = IP_ADDRESS;
if ($xorig ne '') {
# New style Juno has no X-Originating-IP header, and other changes
if($rcvd !~ /from.*\b(?:juno|untd)\.com.*[\[\(]$IP_ADDRESS[\]\)].*by/
&& $rcvd !~ / cookie\.(?:juno|untd)\.com /) { return 1; }
if($xmailer !~ /Juno /) { return 1; }
} else {
if($rcvd =~ /from.*\bmail\.com.*\[$IP_ADDRESS\].*by/) {
if($xmailer !~ /\bmail\.com/) { return 1; }
} elsif($rcvd =~ /from (webmail\S+\.untd\.com) \(\1 \[$IP_ADDRESS\]\) by/) {
if($xmailer !~ /^Webmail Version \d/) { return 1; }
} else {
return 1;
}
if($xorig !~ /$IP_ADDRESS/) { return 1; }
}
return 0;
}
sub check_for_matching_env_and_hdr_from {
my ($self, $pms) =@_;
# two blank headers match so don't bother checking
return (lc $pms->get('EnvelopeFrom:addr') eq lc $pms->get('From:addr'));
}
sub sorted_recipients {
my ($self, $pms) = @_;
if (!exists $pms->{tocc_sorted}) {
$self->_check_recipients($pms);
}
return $pms->{tocc_sorted};
}
sub similar_recipients {
my ($self, $pms, $min, $max) = @_;
if (!exists $pms->{tocc_similar}) {
$self->_check_recipients($pms);
}
return (($min eq 'undef' || $pms->{tocc_similar} >= $min) &&
($max eq 'undef' || $pms->{tocc_similar} < $max));
}
# best experimentally derived values
use constant TOCC_SORTED_COUNT => 7;
use constant TOCC_SIMILAR_COUNT => 5;
use constant TOCC_SIMILAR_LENGTH => 2;
sub _check_recipients {
my ($self, $pms) = @_;
my @inputs;
# ToCc: pseudo-header works best, but sometimes Bcc: is better
for ('ToCc', 'Bcc') {
my $to = $pms->get($_); # get recipients
$to =~ s/\(.*?\)//g; # strip out the (comments)
push(@inputs, ($to =~ m/([\w.=-]+\@\w+(?:[\w.-]+\.)+\w+)/g));
last if scalar(@inputs) >= TOCC_SIMILAR_COUNT;
}
# remove duplicate addresses only when they appear next to each other
my @address;
my $previous = '';
while (my $current = shift @inputs) {
push(@address, ($previous = $current)) if lc($current) ne lc($previous);
last if @address == 256;
}
# ideas that had both poor S/O ratios and poor hit rates:
# - testing for reverse sorted recipient lists
# - testing To: and Cc: headers separately
$pms->{tocc_sorted} = (scalar(@address) >= TOCC_SORTED_COUNT &&
join(',', @address) eq (join(',', sort @address)));
# a good S/O ratio and hit rate is achieved by comparing 2-byte
# substrings and requiring 5 or more addresses
$pms->{tocc_similar} = 0;
if (scalar (@address) >= TOCC_SIMILAR_COUNT) {
my @user = map { substr($_,0,TOCC_SIMILAR_LENGTH) } @address;
my @fqhn = map { m/\@(.*)/ } @address;
my @host = map { substr($_,0,TOCC_SIMILAR_LENGTH) } @fqhn;
my $hits = 0;
my $combinations = 0;
for (my $i = 0; $i <= $#address; $i++) {
for (my $j = $i+1; $j <= $#address; $j++) {
$hits++ if $user[$i] eq $user[$j];
$hits++ if $host[$i] eq $host[$j] && $fqhn[$i] ne $fqhn[$j];
$combinations++;
}
}
$pms->{tocc_similar} = $hits / $combinations;
}
}
sub check_for_missing_to_header {
my ($self, $pms) = @_;
my $hdr = $pms->get('To');
$hdr = $pms->get('Apparently-To') if $hdr eq '';
return 1 if $hdr eq '';
return 0;
}
sub check_for_forged_gw05_received_headers {
my ($self, $pms) = @_;
local ($_);
my $rcv = $pms->get('Received');
# e.g.
# Received: from mail3.icytundra.com by gw05 with ESMTP; Thu, 21 Jun 2001 02:28:32 -0400
my ($h1, $h2) = ($rcv =~
m/\nfrom\s(\S+)\sby\s(\S+)\swith\sESMTP\;\s+\S\S\S,\s+\d+\s+\S\S\S\s+
\d{4}\s+\d\d:\d\d:\d\d\s+[-+]*\d{4}\n$/xs);
if (defined ($h1) && defined ($h2) && $h2 !~ /\./) {
return 1;
}
0;
}
###########################################################################
sub check_for_shifted_date {
my ($self, $pms, $min, $max) = @_;
if (!exists $pms->{date_diff}) {
$self->_check_date_diff($pms);
}
return (($min eq 'undef' || $pms->{date_diff} >= (3600 * $min)) &&
($max eq 'undef' || $pms->{date_diff} < (3600 * $max)));
}
# filters out some false positives in old corpus mail - Allen
sub received_within_months {
my ($self,$pms,$min,$max) = @_;
if (!exists($pms->{date_received})) {
$self->_check_date_received($pms);
}
my $diff = time() - $pms->{date_received};
# 365.2425 * 24 * 60 * 60 = 31556952 = seconds in year (including leap)
if (((! defined($min)) || ($min eq 'undef') ||
($diff >= (31556952 * ($min/12)))) &&
((! defined($max)) || ($max eq 'undef') ||
($diff < (31556952 * ($max/12))))) {
return 1;
} else {
return 0;
}
}
sub _get_date_header_time {
my ($self, $pms) = @_;
my $time;
# a Resent-Date: header takes precedence over any Date: header
DATE: for my $header ('Resent-Date', 'Date') {
my @dates = $pms->{msg}->get_header($header);
for my $date (@dates) {
if (defined($date) && length($date)) {
chomp($date);
$time = Mail::SpamAssassin::Util::parse_rfc822_date($date);
}
last DATE if defined($time);
}
}
if (defined($time)) {
$pms->{date_header_time} = $time;
}
else {
$pms->{date_header_time} = undef;
}
}
sub _get_received_header_times {
my ($self, $pms) = @_;
$pms->{received_header_times} = [ () ];
$pms->{received_fetchmail_time} = undef;
my (@received);
my $received = $pms->get('Received');
if ($received ne '') {
@received = grep {$_ =~ m/\S/} (split(/\n/,$received));
}
# if we have no Received: headers, chances are we're archived mail
# with a limited set of headers
if (!scalar(@received)) {
return;
}
# handle fetchmail headers
my (@local);
if (($received[0] =~
m/\bfrom (?:localhost\s|(?:\S+ ){1,2}\S*\b127\.0\.0\.1\b)/) ||
($received[0] =~ m/qmail \d+ invoked by uid \d+/)) {
push @local, (shift @received);
}
if (scalar(@received) &&
($received[0] =~ m/\bby localhost with \w+ \(fetchmail-[\d.]+/)) {
push @local, (shift @received);
}
elsif (scalar(@local)) {
unshift @received, (shift @local);
}
if (scalar(@local)) {
my (@fetchmail_times);
foreach my $rcvd (@local) {
if ($rcvd =~ m/(\s.?\d+ \S\S\S \d+ \d+:\d+:\d+ \S+)/) {
my $date = $1;
dbg2("eval: trying Received fetchmail header date for real time: $date");
my $time = Mail::SpamAssassin::Util::parse_rfc822_date($date);
if (defined($time) && (time() >= $time)) {
dbg2("eval: time_t from date=$time, rcvd=$date");
push @fetchmail_times, $time;
}
}
}
if (scalar(@fetchmail_times) > 1) {
$pms->{received_fetchmail_time} =
(sort {$b <=> $a} (@fetchmail_times))[0];
} elsif (scalar(@fetchmail_times)) {
$pms->{received_fetchmail_time} = $fetchmail_times[0];
}
}
my (@header_times);
foreach my $rcvd (@received) {
if ($rcvd =~ m/(\s.?\d+ \S\S\S \d+ \d+:\d+:\d+ \S+)/) {
my $date = $1;
dbg2("eval: trying Received header date for real time: $date");
my $time = Mail::SpamAssassin::Util::parse_rfc822_date($date);
if (defined($time)) {
dbg2("eval: time_t from date=$time, rcvd=$date");
push @header_times, $time;
}
}
}
if (scalar(@header_times)) {
$pms->{received_header_times} = [ @header_times ];
} else {
dbg("eval: no dates found in Received headers");
}
}
sub _check_date_received {
my ($self, $pms) = @_;
my (@dates_poss);
$pms->{date_received} = 0;
if (!exists($pms->{date_header_time})) {
$self->_get_date_header_time($pms);
}
if (defined($pms->{date_header_time})) {
push @dates_poss, $pms->{date_header_time};
}
if (!exists($pms->{received_header_times})) {
$self->_get_received_header_times($pms);
}
my (@received_header_times) = @{ $pms->{received_header_times} };
if (scalar(@received_header_times)) {
push @dates_poss, $received_header_times[0];
}
if (defined($pms->{received_fetchmail_time})) {
push @dates_poss, $pms->{received_fetchmail_time};
}
if (defined($pms->{date_header_time}) && scalar(@received_header_times)) {
if (!exists($pms->{date_diff})) {
$self->_check_date_diff($pms);
}
push @dates_poss, $pms->{date_header_time} - $pms->{date_diff};
}
if (scalar(@dates_poss)) { # use median
$pms->{date_received} = (sort {$b <=> $a}
(@dates_poss))[int($#dates_poss/2)];
dbg("eval: date chosen from message: " .
scalar(localtime($pms->{date_received})));
} else {
dbg("eval: no dates found in message");
}
}
sub _check_date_diff {
my ($self, $pms) = @_;
$pms->{date_diff} = 0;
if (!exists($pms->{date_header_time})) {
$self->_get_date_header_time($pms);
}
if (!defined($pms->{date_header_time})) {
return; # already have tests for this
}
if (!exists($pms->{received_header_times})) {
$self->_get_received_header_times($pms);
}
my (@header_times) = @{ $pms->{received_header_times} };
if (!scalar(@header_times)) {
return; # archived mail?
}
my (@diffs) = map {$pms->{date_header_time} - $_} (@header_times);
# if the last Received: header has no difference, then we choose to
# exclude it
if ($#diffs > 0 && $diffs[$#diffs] == 0) {
pop(@diffs);
}
# use the date with the smallest absolute difference
# (experimentally, this results in the fewest false positives)
@diffs = sort { abs($a) <=> abs($b) } @diffs;
$pms->{date_diff} = $diffs[0];
}
sub subject_is_all_caps {
my ($self, $pms) = @_;
my $subject = $pms->get('Subject');
$subject =~ s/^\s+//;
$subject =~ s/\s+$//;
$subject =~ s/^(?:(?:Re|Fwd|Fw|Aw|Antwort|Sv):\s*)+//i; # Bug 6805
return 0 if $subject !~ /\s/; # don't match one word subjects
return 0 if (length $subject < 10); # don't match short subjects
$subject =~ s/[^a-zA-Z]//g; # only look at letters
# now, check to see if the subject is encoded using a non-ASCII charset.
# If so, punt on this test to avoid FPs. We just list the known charsets
# this test will FP on, here.
my $subjraw = $pms->get('Subject:raw');
my $CLTFAC = Mail::SpamAssassin::Constants::CHARSETS_LIKELY_TO_FP_AS_CAPS;
if ($subjraw =~ /=\?${CLTFAC}\?/i) {
return 0;
}
return length($subject) && ($subject eq uc($subject));
}
sub check_for_to_in_subject {
my ($self, $pms, $test) = @_;
my $full_to = $pms->get('To:addr');
return 0 unless $full_to ne '';
my $subject = $pms->get('Subject');
if ($test eq "address") {
return $subject =~ /\b\Q$full_to\E\b/i; # "user@domain.com"
}
elsif ($test eq "user") {
my $to = $full_to;
$to =~ s/\@.*//;
my $subj = $subject;
$subj =~ s/^\s+//;
$subj =~ s/\s+$//;
return $subject =~ /^(?:
(?:re|fw):\s*(?:\w+\s+)?\Q$to\E$
|(?-i:\Q$to\E)\s*[,:;!?-](?:$|\s)
|\Q$to\E$
|,\s*\Q$to\E[,:;!?-]$
)/ix;
}
return 0;
}
sub check_outlook_message_id {
my ($self, $pms) = @_;
local ($_);
my $id = $pms->get('MESSAGEID');
return 0 if $id !~ /^<[0-9a-f]{4}([0-9a-f]{8})\$[0-9a-f]{8}\$[0-9a-f]{8}\@/;
my $timetoken = hex($1);
my $x = 0.0023283064365387;
my $y = 27111902.8329849;
my $fudge = 250;
$_ = $pms->get('Date');
$_ = Mail::SpamAssassin::Util::parse_rfc822_date($_) || 0;
my $expected = int (($_ * $x) + $y);
my $diff = $timetoken - $expected;
return 0 if (abs($diff) < $fudge);
$_ = $pms->get('Received');
/(\s.?\d+ \S\S\S \d+ \d+:\d+:\d+ \S+).*?$/;
$_ = Mail::SpamAssassin::Util::parse_rfc822_date($_) || 0;
$expected = int(($_ * $x) + $y);
$diff = $timetoken - $expected;
return (abs($diff) >= $fudge);
}
sub check_messageid_not_usable {
my ($self, $pms) = @_;
local ($_);
# Lyris eats message-ids. also some ezmlm, I think :(
$_ = $pms->get("List-Unsubscribe");
return 1 if (/<mailto:(?:leave-\S+|\S+-unsubscribe)\@\S+>$/i);
# ezmlm again
if($self->gated_through_received_hdr_remover($pms)) { return 1; }
# Allen notes this as 'Wacky sendmail version?'
$_ = $pms->get("Received");
return 1 if /\/CWT\/DCE\)/;
# Apr 2 2003 jm: iPlanet rewrites lots of stuff, including Message-IDs
return 1 if /iPlanet Messaging Server/;
return 0;
}
# Return true if the count of $hdr headers are within the given range
sub check_header_count_range {
my ($self, $pms, $hdr, $min, $max) = @_;
my %uniq;
my @hdrs = grep(!$uniq{$_}++, $pms->{msg}->get_header ($hdr));
return (scalar @hdrs >= $min && scalar @hdrs <= $max);
}
sub check_unresolved_template {
my ($self, $pms) = @_;
my $all = $pms->get('ALL'); # cached access
$all =~ s/\n[ \t]+/ /gs; # fix continuation lines
for my $header (split(/\n/, $all)) {
# slightly faster to test in this order
if ($header =~ /%[A-Z][A-Z_-]/ &&
$header !~ /^(?:X-VMS-To|X-UIDL|X-Face|To|Cc|From|Subject|References|In-Reply-To|(?:X-|Resent-|X-Original-)?Message-Id):/i)
{
return 1;
}
}
return 0;
}
sub check_ratware_name_id {
my ($self, $pms) = @_;
my $mid = $pms->get('MESSAGEID');
my $from = $pms->get('From');
if ($mid =~ m/<[A-Z]{28}\.([^>]+?)>/) {
if ($from =~ m/\"[^\"]+\"\s*<\Q$1\E>/) {
return 1;
}
}
return 0;
}
sub check_ratware_envelope_from {
my ($self, $pms) = @_;
my $to = $pms->get('To:addr');
my $from = $pms->get('EnvelopeFrom:addr');
return 0 if $from eq '' || $to eq '';
return 0 if $from =~ /^SRS\d=/;
if ($to =~ /^([^@]+)@(.+)$/) {
my($user,$dom) = ($1,$2);
$dom = Mail::SpamAssassin::Util::RegistrarBoundaries::trim_domain($dom);
return unless
(Mail::SpamAssassin::Util::RegistrarBoundaries::is_domain_valid($dom));
return 1 if ($from =~ /\b\Q$dom\E.\Q$user\E@/i);
}
return 0;
}
# ADDED FROM BUG 6487
sub check_equal_from_domains {
my ($self, $pms) = @_;
my $from = $pms->get('From:addr');
my $envfrom = $pms->get('EnvelopeFrom:addr');
local $1;
my $fromdomain = '';
#Revised regexp from 6487 comment 3
$fromdomain = $1 if $from =~ /\@([^@]*)\z/;
$fromdomain =~ s/^.+\.([^\.]+\.[^\.]+)$/$1/;
return 0 if $fromdomain eq '';
my $envfromdomain = '';
$envfromdomain = $1 if $envfrom =~ /\@([^@]*)\z/;
$envfromdomain =~ s/^.+\.([^\.]+\.[^\.]+)$/$1/;
return 0 if $envfromdomain eq '';
dbg("eval: From 2nd level domain: $fromdomain, EnvelopeFrom 2nd level domain: $envfromdomain");
return 1 if lc($fromdomain) ne lc($envfromdomain);
return 0;
}
###########################################################################
# support eval-test verbose debugs using "-Deval"
sub dbg2 {
if (would_log('dbg', 'eval') == 2) {
dbg(@_);
}
}
1;
|