1 # SARE HTML Ruleset for SpamAssassin - ruleset 2
5 # Usage instructions, documentation, and change history in 70_sare_html0.cf
7 #@@# Revision History: Full Revision History stored in 70_sare_html.log
8 #@@# 01.03.09: May ?? 2006
9 #@@# Minor score tweaks based on recent mass-checks
10 #@@# Moved file 0 to file 2: SARE_HTML_EHTML_OBFU
11 #@@# Moved file 0 to file 2: SARE_HTML_HEAD_AFFIL
12 #@@# Moved file 0 to file 2: SARE_HTML_LEAKTHRU1
13 #@@# Moved file 0 to file 2: SARE_HTML_LEAKTHRU2
14 #@@# Moved file 0 to file 2: SARE_HTML_ONE_LINE3
15 #@@# Moved file 0 to file 2: SARE_HTML_POB1200
16 #@@# Moved file 0 to file 2: SARE_HTML_URI_HIDADD
17 #@@# Moved file 0 to file 2: SARE_HTML_URI_LOGOGEN
18 #@@# Moved file 0 to file 2: SARE_HTML_URI_OFF
19 #@@# Moved file 0 to file 2: SARE_HTML_USL_B7
20 #@@# Moved file 0 to file 2: SARE_HTML_USL_B9
21 #@@# Moved file 0 to file 2: SARE_PHISH_HTML_01
22 #@@# 01.03.10: June 3 2006
23 #@@# Minor score tweaks based on recent mass-checks
24 #@@# Moved file 1 to 2: SARE_HTML_BR_MANY
25 #@@# Moved file 1 to 2: SARE_HTML_ONE_LINE2
26 #@@# Moved file 1 to 2: SARE_HTML_URI_OC
28 # License: Artistic - see http://www.rulesemporium.com/license.txt
29 # Current Maintainer: Bob Menschel - RMSA@Menschel.net
30 # Current Home: http://www.rulesemporium.com/rules/70_sare_html2.cf
32 ######## ###################### ##################################################
34 rawbody __SARE_HTML_HAS_A eval:html_tag_exists('a')
35 rawbody __SARE_HTML_HAS_BR eval:html_tag_exists('br')
36 rawbody __SARE_HTML_HAS_DIV eval:html_tag_exists('div')
37 rawbody __SARE_HTML_HAS_FONT eval:html_tag_exists('font')
38 rawbody __SARE_HTML_HAS_IMG eval:html_tag_exists('img')
39 rawbody __SARE_HTML_HAS_P eval:html_tag_exists('p')
40 rawbody __SARE_HTML_HAS_PRE eval:html_tag_exists('pre')
41 rawbody __SARE_HTML_HAS_TITLE eval:html_tag_exists('title')
43 rawbody __SARE_HTML_HBODY m'<html><body>'i
44 rawbody __SARE_HTML_BEHTML m'<body></html>'i
45 rawbody __SARE_HTML_BEHTML2 m'^</?body></html>'i
46 rawbody __SARE_HTML_EFONT m'^</font>'i
47 rawbody __SARE_HTML_EHEB m'^</html></body>'i
48 rawbody __SARE_HTML_CMT_CNTR /<center><!--/
50 ######## ###################### ##################################################
51 # <HTML> and <BODY> tag spamsign
52 ######## ###################### ##################################################
54 rawbody SARE_HTML_EHTML_OBFU m'<\s*/\s+(?!html)[HTmL\s]{4,}>'i
55 describe SARE_HTML_EHTML_OBFU Phoney tag
56 score SARE_HTML_EHTML_OBFU 1.111
57 #stype SARE_HTML_EHTML_OBFU spamp
58 #hist SARE_HTML_EHTML_OBFU Loren Wilton, June 2005
59 #counts SARE_HTML_EHTML_OBFU 0s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
60 #max SARE_HTML_EHTML_OBFU 30s/0h of 619677 corpus (318875s/300802h RM) 09/11/05
61 #counts SARE_HTML_EHTML_OBFU 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
62 #counts SARE_HTML_EHTML_OBFU 0s/0h of 6804 corpus (1336s/5468h ft) 06/17/05
63 #counts SARE_HTML_EHTML_OBFU 21s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
64 #counts SARE_HTML_EHTML_OBFU 0s/0h of 23068 corpus (17346s/5722h MY) 05/14/06
65 #max SARE_HTML_EHTML_OBFU 34s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
67 ######## ###################### ##################################################
68 # Spamsign character sets and fonts
69 ######## ###################### ##################################################
71 rawbody SARE_HTML_COLOR_D /(?:style="?|<style[^>]*>)[^>"]*[^-]color\s*:\s*rgb\(\s*(?:100|9[0-9]|8[6-9])\s*%\s*,\s*(?:100|9[0-9]|8[6-9])\s*%\s*,\s*(?:100|9[0-9]|8[6-9])\s*%\s*\)[^>]*>/i
72 describe SARE_HTML_COLOR_D BAD STYLE: color: too light (rgb(%))
73 score SARE_HTML_COLOR_D 0.100
74 #hist SARE_HTML_COLOR_D From Jesse Houwing May 14 2004
75 #counts SARE_HTML_COLOR_D 0s/0h of 98435 corpus (76828s/21607h RM) 05/14/04
76 #counts SARE_HTML_COLOR_D 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
78 rawbody SARE_HTML_POB1200 /width="599" bgColor="\#9999FF"/i
79 describe SARE_HTML_POB1200 Used by POB1200 Orangestad spammer
80 score SARE_HTML_POB1200 1.666
81 #stype SARE_HTML_POB1200 spamp
82 #hist SARE_HTML_POB1200 Jennifer Wheeler <jennifer.sare@nxtek.net> May 17 2004
83 #counts SARE_HTML_POB1200 0s/0h of 196681 corpus (96193s/100488h RM) 02/22/05
84 #max SARE_HTML_POB1200 414s/0h of 114422 corpus (81069s/33353h RM) 01/16/05
85 #counts SARE_HTML_POB1200 1s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
86 #max SARE_HTML_POB1200 18s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
87 #counts SARE_HTML_POB1200 0s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
88 #max SARE_HTML_POB1200 42s/0h of 18153 corpus (15872s/2281h MY) 05/18/04
89 #counts SARE_HTML_POB1200 0s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
91 ######## ###################### ##################################################
93 ######## ###################### ##################################################
95 rawbody SARE_HTML_NOFRAMES /<frame><noframes>\w*<\/noframes><\/frame>/i
96 describe SARE_HTML_NOFRAMES Body appears to hide anti-anti-spam text in frame
97 score SARE_HTML_NOFRAMES 1.000
98 #counts SARE_HTML_NOFRAMES 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
99 #max SARE_HTML_NOFRAMES 96 spam, 0 ham, Sep 5 2003
100 #counts SARE_HTML_NOFRAMES 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
102 ######## ###################### ##################################################
103 # Invalid or Suspicious URI Tests
104 ######## ###################### ##################################################
106 rawbody SARE_HTML_URI_GBYE />Good Bye<\/a>/i
107 describe SARE_HTML_URI_GBYE text has URL to spammer's unsubscribe link
108 score SARE_HTML_URI_GBYE 0.100
109 #counts SARE_HTML_URI_GBYE 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
110 #counts SARE_HTML_URI_GBYE 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
112 #overlap SARE_HTML_URI_HIDADD Overlaps completely within SARE_HTML_P_BREAK 2004-06-11
113 rawbody SARE_HTML_URI_HIDADD /(?:\&\~c\&o\&m|\&\~n\&e\&t)/i
114 describe SARE_HTML_URI_HIDADD URI with obfuscated destination
115 score SARE_HTML_URI_HIDADD 1.666
116 #stype SARE_HTML_URI_HIDADD spamp
117 #hist SARE_HTML_URI_HIDADD Fred T: FR_HIDDEN_ADDY
118 #overlap SARE_HTML_URI_HIDADD Overlaps completely within SARE_HTML_P_BREAK 2004-06-11
119 #counts SARE_HTML_URI_HIDADD 0s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
120 #max SARE_HTML_URI_HIDADD 817s/0h of 400504 corpus (178155s/222349h RM) 03/31/05
121 #counts SARE_HTML_URI_HIDADD 0s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
122 #max SARE_HTML_URI_HIDADD 2s/0h of 32260 corpus (8983s/23277h JH) 05/14/04
123 #counts SARE_HTML_URI_HIDADD 0s/0h of 23068 corpus (17346s/5722h MY) 05/14/06
124 #max SARE_HTML_URI_HIDADD 1s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
125 #counts SARE_HTML_URI_HIDADD 0s/0h of 10629 corpus (5847s/4782h CT) 09/18/05
127 uri SARE_HTML_URI_HIDE1 /:ac=[A-Z,a-z,0-9,@,!,;]+/
128 describe SARE_HTML_URI_HIDE1 URI attempts to hide destination domain
129 score SARE_HTML_URI_HIDE1 0.100
130 #counts SARE_HTML_URI_HIDE1 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
131 #counts SARE_HTML_URI_HIDE1 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
133 uri SARE_HTML_URI_LOGOGEN m{/logogen\.img\?}i
134 score SARE_HTML_URI_LOGOGEN 1.666
135 describe SARE_HTML_URI_LOGOGEN Uses some logo generation software
136 #hist SARE_HTML_URI_LOGOGEN Jesse Houwing, Aug 19 2004
137 #counts SARE_HTML_URI_LOGOGEN 0s/0h of 175738 corpus (98979s/76759h RM) 02/14/05
138 #max SARE_HTML_URI_LOGOGEN 6s/0h of 65858 corpus (40621s/25237h RM) 08/19/04
139 #counts SARE_HTML_URI_LOGOGEN 319s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
140 #max SARE_HTML_URI_LOGOGEN 453s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
141 #counts SARE_HTML_URI_LOGOGEN 0s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
142 #max SARE_HTML_URI_LOGOGEN 48s/0h of 18647 corpus (16116s/2531h MY) 08/25/04
143 #counts SARE_HTML_URI_LOGOGEN 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
144 #max SARE_HTML_URI_LOGOGEN 7s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
146 uri SARE_HTML_URI_OC /\?oc=\d{4,10}/
147 describe SARE_HTML_URI_OC Possible spammer sign in URL
148 score SARE_HTML_URI_OC 1.666
149 #hist SARE_HTML_URI_OC LW_URI_OC
150 #counts SARE_HTML_URI_OC 0s/0h of 689155 corpus (348140s/341015h RM) 09/18/05
151 #max SARE_HTML_URI_OC 440s/0h of 89461 corpus (67464s/21997h RM) 05/29/04
152 #counts SARE_HTML_URI_OC 0s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
153 #max SARE_HTML_URI_OC 17s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
154 #counts SARE_HTML_URI_OC 0s/0h of 26326 corpus (22886s/3440h MY) 02/15/05
155 #max SARE_HTML_URI_OC 85s/0h of 13454 corpus (11339s/2115h MY) 06/02/04
157 uri SARE_HTML_URI_OFF /http.{5,35}\boff\.(?:htm|html|php|asp|pl|cgi|jsp)\b/i
158 describe SARE_HTML_URI_OFF URI to page name which suggests spammer's page
159 score SARE_HTML_URI_OFF 2.222
160 #hist SARE_HTML_URI_OFF FR_PAGE_OFF
161 #counts SARE_HTML_URI_OFF 0s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
162 #max SARE_HTML_URI_OFF 2619s/0h of 109180 corpus (88746s/20434h RM) 04/09/04
163 #counts SARE_HTML_URI_OFF 2s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
164 #max SARE_HTML_URI_OFF 89s/0h of 32260 corpus (8983s/23277h JH) 05/14/04
165 #counts SARE_HTML_URI_OFF 0s/0h of 26326 corpus (22886s/3440h MY) 02/15/05
166 #counts SARE_HTML_URI_OFF 0s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
167 #max SARE_HTML_URI_OFF 39s/0h of 6944 corpus (3188s/3756h CT) 05/19/04
169 ######## ###################### ##################################################
171 ######## ###################### ##################################################
173 rawbody SARE_HTML_HEAD_AFFIL /\<h[0-9]\>.{2,30}\/.{1,3}affiliate.{1,20}\<\/h[0-9]\>/i
174 describe SARE_HTML_HEAD_AFFIL Affiliate in BOLD
175 score SARE_HTML_HEAD_AFFIL 0.744
176 #hist SARE_HTML_HEAD_AFFIL Matt Yackley, Apr 15 2005
177 #counts SARE_HTML_HEAD_AFFIL 0s/0h of 619677 corpus (318875s/300802h RM) 09/11/05
178 #max SARE_HTML_HEAD_AFFIL 23s/0h of 292246 corpus (119174s/173072h RM) 04/15/05
179 #counts SARE_HTML_HEAD_AFFIL 0s/0h of 13290 corpus (7418s/5872h CT) 05/14/06
180 #max SARE_HTML_HEAD_AFFIL 1s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
181 #counts SARE_HTML_HEAD_AFFIL 0s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
182 #counts SARE_HTML_HEAD_AFFIL 0s/0h of 23068 corpus (17346s/5722h MY) 05/14/06
183 #max SARE_HTML_HEAD_AFFIL 10s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
185 ######## ###################### ##################################################
186 # Suspicious tag combinations
187 ######## ###################### ##################################################
189 rawbody SARE_HTML_ONE_LINE2 m'<body><p><a href="http://\w+\.\w+\.info/\?[\w\.]+"><IMG SRC="cid:[\w\@\.]+" border="0" ALT=""></a>'
190 describe SARE_HTML_ONE_LINE2 standard spam formatting
191 score SARE_HTML_ONE_LINE2 1.111
192 #stype SARE_HTML_ONE_LINE2 spamp
193 #hist SARE_HTML_ONE_LINE2 Loren Wilton, LW_SINGLELINE4 Sep 5 2004
194 #counts SARE_HTML_ONE_LINE2 0s/0h of 281655 corpus (110173s/171482h RM) 05/05/05
195 #max SARE_HTML_ONE_LINE2 22s/0h of 114422 corpus (81069s/33353h RM) 01/16/05
196 #counts SARE_HTML_ONE_LINE2 1s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
197 #counts SARE_HTML_ONE_LINE2 0s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
198 #max SARE_HTML_ONE_LINE2 5s/0h of 26326 corpus (22886s/3440h MY) 02/15/05
200 full SARE_HTML_ONE_LINE3 m'\n<html><body>\n<center>.{0,140}</center>\n</body></html>\n'
201 describe SARE_HTML_ONE_LINE3 Another single-line centered HTML message
202 score SARE_HTML_ONE_LINE3 1.256
203 #hist SARE_HTML_ONE_LINE3 Loren Wilton: LW_SINGLELINE4
204 #counts SARE_HTML_ONE_LINE3 0s/0h of 281271 corpus (109792s/171479h RM) 05/05/05
205 #max SARE_HTML_ONE_LINE3 64s/0h of 70245 corpus (42816s/27429h RM) 10/02/04
206 #counts SARE_HTML_ONE_LINE3 61s/0h of 54969 corpus (17793s/37176h JH-3.01) 03/13/05
207 #counts SARE_HTML_ONE_LINE3 0s/0h of 19447 corpus (16862s/2585h MY) 10/06/04
208 #counts SARE_HTML_ONE_LINE3 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
209 #max SARE_HTML_ONE_LINE3 1s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
211 rawbody SARE_HTML_LEAKTHRU1 m'^<BODY><p><(\w+)></(?:\1)><A href=\"[^"]+\"><(\w+)></(?:\2)>$'
212 score SARE_HTML_LEAKTHRU1 1.111
213 #stype SARE_HTML_LEAKTHRU1 spamp
214 #hist SARE_HTML_LEAKTHRU1 Loren Wilton: LW_LEAKTHRU
215 describe SARE_HTML_LEAKTHRU1 Another image-only spam
216 #counts SARE_HTML_LEAKTHRU1 0s/0h of 619677 corpus (318875s/300802h RM) 09/11/05
217 #max SARE_HTML_LEAKTHRU1 72s/0h of 196642 corpus (96193s/100449h RM) 02/22/05
218 #counts SARE_HTML_LEAKTHRU1 0s/0h of 54969 corpus (17793s/37176h JH-3.01) 03/13/05
219 #counts SARE_HTML_LEAKTHRU1 0s/0h of 23068 corpus (17346s/5722h MY) 05/14/06
220 #max SARE_HTML_LEAKTHRU1 22s/0h of 31513 corpus (27912s/3601h MY) 03/09/05
221 #counts SARE_HTML_LEAKTHRU1 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
223 rawbody SARE_HTML_LEAKTHRU2 m'^<BODY><p><(\w+)(?:\s[\w\=]+)?></(?:\1)><A href=\"[^"]+\"><(\w+)(?:\s[\w\=]+)?></(?:\2)>$'
224 score SARE_HTML_LEAKTHRU2 1.666
225 #stype SARE_HTML_LEAKTHRU2 spamp
226 #hist SARE_HTML_LEAKTHRU2 Loren Wilton: LW_LEAKTHRU1
227 describe SARE_HTML_LEAKTHRU2 Another image-only spam
228 #counts SARE_HTML_LEAKTHRU2 0s/0h of 619677 corpus (318875s/300802h RM) 09/11/05
229 #max SARE_HTML_LEAKTHRU2 178s/0h of 283600 corpus (129945s/153655h RM) 03/08/05
230 #counts SARE_HTML_LEAKTHRU2 0s/0h of 54969 corpus (17793s/37176h JH-3.01) 03/13/05
231 #counts SARE_HTML_LEAKTHRU2 0s/0h of 23068 corpus (17346s/5722h MY) 05/14/06
232 #max SARE_HTML_LEAKTHRU2 48s/0h of 31513 corpus (27912s/3601h MY) 03/09/05
233 #counts SARE_HTML_LEAKTHRU2 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
235 ######## ###################### ##################################################
236 # Useless tags (tag structures that do nothing)
237 # Largely submitted by Matt Yackley, with contributions by
238 # Carl Friend, Jennifer Wheeler, Scott Sprunger, Larry Gilson
239 ######## ###################### ##################################################
241 rawbody SARE_HTML_USL_B7 /(<b><\/b>.{1,5}){7,8}/i
242 describe SARE_HTML_USL_B7 Multiple <b></b> (7-8)
243 score SARE_HTML_USL_B7 0.100
244 #counts SARE_HTML_USL_B7 0s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
245 #max SARE_HTML_USL_B7 105s/0h of 689155 corpus (348140s/341015h RM) 09/18/05
246 #counts SARE_HTML_USL_B7 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
247 #counts SARE_HTML_USL_B7 0s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
249 rawbody SARE_HTML_USL_B9 /(<b><\/b>.{1,5}){9,10}/i
250 describe SARE_HTML_USL_B9 Multiple <b></b> (9-10)
251 score SARE_HTML_USL_B9 0.100
252 #counts SARE_HTML_USL_B9 0s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
253 #max SARE_HTML_USL_B9 99s/0h of 689155 corpus (348140s/341015h RM) 09/18/05
254 #counts SARE_HTML_USL_B9 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
255 #counts SARE_HTML_USL_B9 0s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
257 ######## ###################### ##################################################
258 # <tag ... ALT= ...> tag tests
259 ######## ###################### ##################################################
261 ######## ###################### ##################################################
262 # <!-- Comment tag tests
263 ######## ###################### ##################################################
265 rawbody SARE_HTML_CMT_MONEY /<\!--\${1,10}-->/i
266 describe SARE_HTML_CMT_MONEY HTML Comment seems to mention money
267 score SARE_HTML_CMT_MONEY 0.100
268 #counts SARE_HTML_CMT_MONEY 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
269 #counts SARE_HTML_CMT_MONEY 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
271 ######## ###################### ##################################################
273 ######## ###################### ##################################################
275 rawbody SARE_HTML_GIF_NUM /\.gif\d{2,}/i
276 describe SARE_HTML_GIF_NUM HTML contains tracking numbers after .gif
277 score SARE_HTML_GIF_NUM 0.100
278 #counts SARE_HTML_GIF_NUM 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
279 #counts SARE_HTML_GIF_NUM 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
281 ######## ###################### ##################################################
282 # Paragraphs, breaks, and spacings
283 ######## ###################### ##################################################
285 rawbody SARE_HTML_BR_MANY /<br>{5}/i
286 describe SARE_HTML_BR_MANY Too many sequential identical HTML tags
287 score SARE_HTML_BR_MANY 0.555
288 #stype SARE_HTML_BR_MANY spamp
289 #counts SARE_HTML_BR_MANY 0s/0h of 689155 corpus (348140s/341015h RM) 09/18/05
290 #max SARE_HTML_BR_MANY 2s/0h of 258858 corpus (114246s/144612h RM) 05/27/05
291 #counts SARE_HTML_BR_MANY 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
292 #counts SARE_HTML_BR_MANY 0s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
293 #counts SARE_HTML_BR_MANY 0s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
295 rawbody __SARE_HTML_MANY_BR05 /<br>\s*<br>\s*<br>\s*<br>\s*<br>\s*<br>/i
296 meta SARE_HTML_MANY_BR05 __SARE_HTML_MANY_BR05 && HTML_MESSAGE
297 describe SARE_HTML_MANY_BR05 Tooo many <br>'s!
298 score SARE_HTML_MANY_BR05 0.500
299 #hist SARE_HTML_MANY_BR05 Contrib by Matt Keller June 7 2004
300 #note SARE_HTML_MANY_BR05 Remove HTML_MESSAGE test increases spam 4% but doubles ham
301 #hist SARE_HTML_MANY_BR05 this and SARE_HTML_MANY_BR10 obsolete SARE_HTML_TD_BR4 = FR_WICKED_SPAM_??
302 #counts SARE_HTML_MANY_BR05 0s/0h of 114422 corpus (81069s/33353h RM) 01/16/05
303 #alone SARE_HTML_MANY_BR05 2051s/43h of 66351 corpus (40971s/25380h RM) 08/21/04
304 #counts SARE_HTML_MANY_BR05 0s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
305 #max SARE_HTML_MANY_BR05 755s/2h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
306 #counts SARE_HTML_MANY_BR05 0s/0h of 26326 corpus (22886s/3440h MY) 02/15/05
308 ######## ###################### ##################################################
309 # Javascript and object tests
310 ######## ###################### ##################################################
312 rawbody SARE_HTML_JVS_POPUP /<body onload \= \"window\.open/i
313 describe SARE_HTML_JVS_POPUP Bad HTML form. Tries to load a javascript pop up.
314 score SARE_HTML_JVS_POPUP 0.100
315 #counts SARE_HTML_JVS_POPUP 0s/0h of 98542 corpus (76935s/21607h RM) 05/12/04
316 #counts SARE_HTML_JVS_POPUP 0s/0h of 29365 corpus (5882s/23483h JH) 08/14/04 TM2 SA3.0-pre2
318 ######## ###################### ##################################################
319 # Tests destined for other rule sets
320 ######## ###################### ##################################################
322 full __SARE_PHISH_HTML_01a m*<a[^<]{0,60} onMouseMove=(?:3D)?"window.status=(?:3D)?'https?://*
323 rawbody __SARE_PHISH_HTML_01b m*<a[^<]{0,60} onMouseMove=(?:3D)?"window.status=(?:3D)?'https?://*
324 meta SARE_PHISH_HTML_01 __SARE_PHISH_HTML_01a || __SARE_PHISH_HTML_01b
325 describe SARE_PHISH_HTML_01 Hiding actual site with fake secure site!
326 score SARE_PHISH_HTML_01 2.500
327 #stype SARE_PHISH_HTML_01 spamgg # phish
328 #hist SARE_PHISH_HTML_01 Loren Wilton: LW_MOUSEMOVE
329 #counts SARE_PHISH_HTML_01 1s/0h of 619677 corpus (318875s/300802h RM) 09/11/05
330 #max SARE_PHISH_HTML_01 17s/0h of 70245 corpus (42816s/27429h RM) 10/02/04
331 #counts SARE_PHISH_HTML_01 2s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
332 #max SARE_PHISH_HTML_01 5s/0h of 54969 corpus (17793s/37176h JH-3.01) 03/13/05
333 #counts SARE_PHISH_HTML_01 0s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
334 #max SARE_PHISH_HTML_01 6s/0h of 19447 corpus (16862s/2585h MY) 10/06/04
335 #counts SARE_PHISH_HTML_01 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05