| # SpamAssassin rules file: Pdfinfo rules |
| # |
| # Please don't modify this file as your changes will be overwritten with |
| # the next update. Use @@LOCAL_RULES_DIR@@/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> |
| # |
| ########################################################################### |
| |
| # 2014-12-02 - axb |
| # Info and disabled rules kept for historical & documentation reasons |
| # Updated rules may be added |
| # |
| # Original File: pdfinfo.cf |
| # Original Version: 0.6 |
| # Info: $Id: pdfinfo.cf 895 2007-07-27 10:31:08Z alexb $ |
| # Created: 2007-06-25 |
| # Modified: 2007-07-19 |
| # Original / Defunct Site URL: http://www.rulesemporium.com/plugins.htm#PDFinfo |
| # Author: Dallas Engelken (aka GMD :-) |
| # Rules contributed by Alex Broens |
| # Requires: PDFInfo.pm plugin |
| # Description: This plugin/ruleset combination will help you alleviate the new |
| # PDF based stock spam which began to appear mid-June, 2007. |
| # |
| # |
| # Changes: |
| # |
| # 0.6 - added easypdf producer rule and more no body text metas |
| # - tags support added, see USING TAGS below. |
| # 0.5 - added fuzzy test 7 |
| # 0.4 - added new fuzzy for encyprted pdf image spams. |
| # - added rule to check for encryption |
| # 0.3 - added rules based on the new pdf_match_details() function |
| # - added additional fuzzy md5 rules |
| # - disabled static md5 rules as they are no longer hitting. |
| # 0.2 - added static md5 to hit full page stock spam. |
| # 0.1 - initial ruleset. |
| # |
| |
| ############################################ |
| # USING TAGS |
| ############################################ |
| |
| # The follow tags can be defined in an add_header line |
| # |
| # _PDFCOUNT_ - total number of pdf mime parts in the email |
| # _PDFIMGCOUNT_ - total number of images found inside pdf mime parts |
| # _PDFVERSION_ - PDF Version, space seperated if there are > 1 pdf attachments |
| # _PDFNAME_ - Filenames as found in the mime headers of PDF parts |
| # _PDFPRODUCER_ - Producer/Application that created the PDF(s) |
| # _PDFAUTHOR_ - Author of the PDF |
| # _PDFCREATOR_ - Creator/Program that created the PDF(s) |
| # _PDFTITLE_ - Title of the PDF File, if available |
| # _PDFIMGDIM_ - If PDF Contains images, the dimensions of them will be put here |
| # _PDFIMGAREA_ - The total area of all combined images inside the PDF(s) |
| # _PDFMD5_ - MD5 checksum of PDF(s) - space seperated |
| # _PDFMD5FUZZY1_- Fuzzy1 MD5 checksum of PDF(s) - space seperated |
| # _PDFMD5FUZZY2_- Fuzzy2 MD5 checksum of PDF(s) - space seperated |
| # |
| # Example add_header lines |
| # |
| # add_header all PDF-Info pdf=_PDFCOUNT_, pdfimg=_PDFIMGCOUNT_, ver=_PDFVERSION_, name=_PDFNAME_ |
| # add_header all PDF-Details producer=_PDFPRODUCER_, author=_PDFAUTHOR_, creator=_PDFCREATOR_, title=_PDFTITLE_ |
| # add_header all PDF-ImageInfo dim=_PDFIMGDIM_, area=_PDFIMGAREA_ |
| # add_header all PDF-Md5 md5=_PDFMD5_, fuzzy1=_PDFMD5FUZZY1_, fuzzy2=_PDFMD5FUZZY2_ |
| # |
| |
| ############################################ |
| # GENERIC RULE EXAMPLES SHOWING EVAL USAGE |
| ############################################ |
| |
| # you can match by name |
| # body MY_TEST_PDF eval:pdf_named('mytest.pdf') |
| |
| # or you can write a regex to match dynamic file names. |
| # body MY_TEST_PDF eval:pdf_name_regex('/^(?:my|your)test\.pdf$/') |
| |
| # you can make it case insensitive by using modifiers |
| # body PDF_IMGXXXXX eval:pdf_name_regex('/^IMG\D+\.\.PDF$/i') |
| |
| # you can do exact image size matches |
| # body PDF_DEMS_150_400 eval:pdf_image_size_exact(150,400) |
| |
| # you can do image to text, or image to html ratios |
| # rawbody PDF_TO_HTML_RATIO eval:pdf_image_to_text_ratio(0.000, 0.015) |
| # body PDF_TO_TEXT_RATIO eval:pdf_image_to_text_ratio(0.000, 0.008) |
| |
| # you can do minimum demension matches |
| # body PDF_SIZE_RANGE_1 eval:pdf_image_size_range(300,300) |
| |
| # you can do ranged demension matches |
| # body PDF_SIZE_RANGE_2 eval:pdf_image_size_range(200, 300, 250, 350) |
| |
| # you can count the number of pdf mime partts |
| # body PDF_MIME_COUNT_1 eval:pdf_count(1,1) |
| # body PDF_MIME_COUNT_2_PLUS eval:pdf_count(2) |
| |
| # you can count the number of images inside the pdfs |
| # body PDF_IMG_COUNT_1 eval:pdf_image_count(1,1) |
| # body PDF_IMG_COUNT_2_PLUS eval:pdf_image_count(2) |
| |
| # you can determine pixel coverage |
| # body PDF_AREA_SMALL eval:pdf_pixel_coverage(1,100000) |
| |
| |
| # match a md5 or fuzzy md5 signature of the pdf |
| |
| # body PDF_BAD_MD5 eval:pdf_match_md5('C359F8F89B290DA99DC997ED50117CDF') |
| # body PDF_BAD_FUZZY eval:pdf_match_fuzzy_md5('7340821445D975EEF6F5BDE2EC257900') |
| |
| # Now you can match against certain details if they are found in the PDF. |
| # A regex match is used on the value specified, so if you want to do an |
| # exact match, use anchors ^value$ |
| # |
| # body GMD_AUTHOR_MOBILE eval:pdf_match_details('author','/^mobile$/') |
| # body GMD_PRODUCER_GPL eval:pdf_match_details('producer','/(?i)^gpl ghostscript/') |
| # body GMD_CREATOR_PSCRIPT5 eval:pdf_match_details('creator','/^PScript5/') |
| # body GMD_TITLE_WORD_DOC1 eval:pdf_match_details('title','/^Microsoft Word \- Document1$/) |
| # body GMD_CREATED_JULY07 eval:pdf_match_details('created','/^200707/') |
| # body GMD_MODIFIED_JULY07 eval:pdf_match_details('modified','/^200707/') |
| |
| ifplugin Mail::SpamAssassin::Plugin::PDFInfo |
| |
| ####################################### |
| # DISABLED RULES, ENABLE IF YOU WANT |
| ####################################### |
| |
| # Small area |
| # Disabled - Hits Ham |
| # body GMD_PDF_SMALL_AREA eval:pdf_pixel_coverage(1,100000) |
| # describe GMD_PDF_SMALL_AREA PDF Area covers 150k pixels or less |
| # score GMD_PDF_SMALL_AREA 0.75 |
| # counts GMD_PDF_SMALL_AREA 51s/15h of 10615 corpus (5652s/4963h AxB) 06/25/07 |
| |
| # NOTE - people do send pdf's without message bodies! |
| # Disabled - Hits Ham |
| # body GMD_PDF_NO_TXT eval:pdf_image_to_text_ratio(0.000, 0.005) |
| # describe GMD_PDF_NO_TXT Low rawbody to pixel area ratio |
| # score GMD_PDF_NO_TXT 0.01 |
| # counts GMD_PDF_NO_TXT 64s/3h of 10615 corpus (5652s/4963h AxB) 06/25/07 |
| |
| #################################### |
| # HERE ARE THE LIVE RULES |
| #################################### |
| |
| |
| |
| ###################################################################################################### |
| # pdf image dimensions |
| |
| # thin horizontal, common stox. |
| body GMD_PDF_HORIZ eval:pdf_image_size_range(100, 450, 240, 800) |
| describe GMD_PDF_HORIZ Contains pdf 100-240 (high) x 450-800 (wide) |
| score GMD_PDF_HORIZ 0.25 |
| # counts GMD_PDF_HORIZ 135s/0h of 6132 corpus (4555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PDF_HORIZ 278s/0h of 34051 corpus (33259s/792h AxB2-TRAPS) 07/13/07 |
| |
| # near square, and small. common stox. |
| body GMD_PDF_SQUARE eval:pdf_image_size_range(180, 180, 360, 360) |
| describe GMD_PDF_SQUARE Contains pdf 180-360 (high) x 180-360 (wide) |
| score GMD_PDF_SQUARE 0.50 |
| # counts GMD_PDF_SQUARE 36s/0h of 6132 corpus (4555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PDF_SQUARE 46s/0h of 34051 corpus (33259s/792h AxB2-TRAPS) 07/13/07 |
| |
| # thin vertical, very tall. common stox. |
| body GMD_PDF_VERT eval:pdf_image_size_range(450, 100, 800, 240) |
| describe GMD_PDF_VERT Contains pdf 450-800 (high) x 100-240 (wide) |
| score GMD_PDF_VERT 0.90 |
| # counts GMD_PDF_VERT 24s/0h of 6132 corpus (4555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PDF_VERT 10s/0h of 11773 corpus (10988s/785h AxB2-TRAPS) 07/11/07 |
| |
| ###################################################################################################### |
| # static checksums |
| |
| # all static md5 spam runs are complete as of 7/11 |
| # if there are more, we'll add new rules. |
| |
| # removed fuzzy rules dated 2007 |
| # Get fuzzy info: |
| # cat msg.eml | spamassassin --debug pdfinfo 2>&1 | grep fuzzy 2>&1 |
| |
| # sample rules ONLY |
| # fuzzy checksum for bad stox |
| #body GMD_PDF_FUZZY1_T1 eval:pdf_match_fuzzy_md5('57EBC1FFB1A24CC14AE23E1E227C3484') |
| #describe GMD_PDF_FUZZY1_T1 Fuzzy MD5 Match 57EBC1FFB1A24CC14AE23E1E227C3484 |
| #score GMD_PDF_FUZZY1_T1 0.001 |
| |
| # same as rule above using fuzzy md5 of pdf structure |
| #body GMD_PDF_FUZZY2_T1 eval:pdf_match_fuzzy_md5('653C8AA9FDFD03D382523488058360A2') |
| #describe GMD_PDF_FUZZY2_T1 Fuzzy MD5 Match 653C8AA9FDFD03D382523488058360A2 |
| #score GMD_PDF_FUZZY2_T1 0.001 |
| |
| |
| ###################################################################################################### |
| # pdf_match_details() |
| |
| # from embedded link spam |
| #body GMD_AUTHOR_COLET eval:pdf_match_details('author','/^colet$/') |
| #describe GMD_AUTHOR_COLET PDF author was 'colet' |
| #score GMD_AUTHOR_COLET 4.50 |
| # counts GMD_AUTHOR_COLET 1s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| # counts GMD_AUTHOR_COLET 2s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| |
| # from full page pdf stock spammer. |
| #body GMD_AUTHOR_MOBILE eval:pdf_match_details('author','/^mobile$/') |
| #describe GMD_AUTHOR_MOBILE PDF author was 'mobile' |
| #score GMD_AUTHOR_MOBILE 2.75 |
| # counts GMD_AUTHOR_MOBILE 2s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_AUTHOR_MOBILE 55s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| |
| # txt only stock spam |
| #body GMD_AUTHOR_OOO eval:pdf_match_details('author','/^openofficeuser$/') |
| #describe GMD_AUTHOR_OOO PDF author was 'openofficeuser' |
| #score GMD_AUTHOR_OOO 1.75 |
| # counts GMD_AUTHOR_OOO 1s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| # counts GMD_AUTHOR_OOO 118s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| |
| # txt only stock spam |
| #body GMD_AUTHOR_HPADMIN eval:pdf_match_details('author','/^HP_Administrator/') |
| #describe GMD_AUTHOR_HPADMIN PDF author was 'HP_Administrator' |
| #score GMD_AUTHOR_HPADMIN 0.25 |
| # counts GMD_AUTHOR_HPADMIN 105s/0h of 6132 corpus (4555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_AUTHOR_HPADMIN 27s/0h of 11773 corpus (10988s/785h AxB2-TRAPS) 07/11/07 |
| |
| # generic rule for software used to produce the pdf. |
| body GMD_PRODUCER_GPL eval:pdf_match_details('producer','/^(?:gnu|gpl) ghostscript/i') |
| describe GMD_PRODUCER_GPL PDF producer was GPL Ghostscript |
| score GMD_PRODUCER_GPL 0.25 |
| # counts GMD_PRODUCER_GPL 227s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PRODUCER_GPL 85s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| |
| # generic rule for software used to produce the pdf. |
| body GMD_PRODUCER_POWERPDF eval:pdf_match_details('producer','/^PowerPdf 0\./') |
| describe GMD_PRODUCER_POWERPDF PDF producer was PowerPDF |
| score GMD_PRODUCER_POWERPDF 0.25 |
| # counts GMD_PRODUCER_POWERPDF 0s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| # counts GMD_PRODUCER_POWERPDF 0s/0h of 5641 corpus (4064s/1577h AxB-MANUAL) 07/11/07 |
| |
| # producer is bcl |
| body GMD_PRODUCER_EASYPDF eval:pdf_match_details('producer','/^BCL easyPDF/') |
| describe GMD_PRODUCER_EASYPDF PDF producer was BCL easyPDF |
| score GMD_PRODUCER_EASYPDF 0.25 |
| |
| # simple check for encryption used inside pdf. |
| # recommend meta with something else... |
| body GMD_PDF_ENCRYPTED eval:pdf_is_encrypted() |
| describe GMD_PDF_ENCRYPTED Attached PDF is encrypted |
| score GMD_PDF_ENCRYPTED 0.60 |
| # counts GMD_PDF_ENCRYPTED 13s/0h of 34051 corpus (33259s/792h AxB2-TRAPS) 07/13/07 |
| |
| # simple check for empty msg body when there is one or more pdf attachments present. |
| body GMD_PDF_EMPTY_BODY eval:pdf_is_empty_body() |
| describe GMD_PDF_EMPTY_BODY Attached PDF with empty message body |
| score GMD_PDF_EMPTY_BODY 0.25 |
| # counts GMD_PDF_EMPTY_BODY 1638s/20h of 27034 corpus (24636s/2398h AxB-MANUAL) 07/19/07 |
| |
| ###################################################################################################### |
| # metas |
| #meta __GMD_PDF_CHECKSUM ( GMD_PDF_FUZZY1_T1 || GMD_PDF_FUZZY2_T1 || GMD_PDF_FUZZY2_T2 || GMD_PDF_FUZZY2_T3 || GMD_PDF_FUZZY2_T4 || GMD_PDF_FUZZY2_T5 || GMD_PDF_FUZZY2_T6 || GMD_PDF_FUZZY2_T7 ||GMD_PDF_FUZZY2_T9 || GMD_PDF_FUZZY2_T10 || GMD_PDF_FUZZY2_T11 || GMD_PDF_FUZZY2_T12 ) |
| #meta __GMD_PDF_DETAIL ( GMD_AUTHOR_COLET || GMD_AUTHOR_MOBILE || GMD_AUTHOR_OOO || GMD_AUTHOR_HPADMIN || GMD_PRODUCER_GPL || GMD_PRODUCER_POWERPDF || GMD_PRODUCER_EASYPDF ) |
| meta __GMD_PDF_DIMS ( GMD_PDF_VERT || GMD_PDF_HORIZ || GMD_PDF_SQUARE ) |
| meta __GMD_PDF_PRODUCERS ( GMD_PRODUCER_GPL || GMD_PRODUCER_POWERPDF || GMD_PRODUCER_EASYPDF ) |
| |
| # rule hits ham by itself, so use just to meta. |
| body __GMD_PDF_NO_TXT eval:pdf_image_to_text_ratio(0.000, 0.005) |
| |
| # meta checksum hit with image dimensions |
| #meta GMD_PDF_STOX_M1 ( __GMD_PDF_CHECKSUM && __GMD_PDF_DIMS) |
| #describe GMD_PDF_STOX_M1 PDF Stox spam |
| #score GMD_PDF_STOX_M1 3.25 |
| # counts GMD_PDF_STOX_M1 159s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PDF_STOX_M1 40s/0h of 11773 corpus (10988s/785h AxB2-TRAPS) 07/11/07 |
| |
| # meta checksum hit to pdf details |
| #meta GMD_PDF_STOX_M2 ( __GMD_PDF_CHECKSUM && __GMD_PDF_DETAIL ) |
| #describe GMD_PDF_STOX_M2 PDF Stox spam |
| #score GMD_PDF_STOX_M2 2.95 |
| # counts GMD_PDF_STOX_M2 223s/0h of 6132 corpus (555s/1577h AxB-MANUAL) 07/11/07 |
| # counts GMD_PDF_STOX_M2 29s/0h of 10767 corpus (9986s/781h AxB2-TRAPS) 07/11/07 |
| |
| # meta dimensions and encryption |
| #meta GMD_PDF_STOX_M3 ( __GMD_PDF_DIMS && GMD_PDF_ENCRYPTED ) |
| #describe GMD_PDF_STOX_M3 PDF Stox spam |
| #score GMD_PDF_STOX_M3 2.25 |
| # counts GMD_PDF_STOX_M3 12s/0h of 34051 corpus (33259s/792h AxB2-TRAPS) 07/13/07 |
| |
| # meta checksum with no text |
| #meta GMD_PDF_STOX_M4 ( __GMD_PDF_CHECKSUM && (__GMD_PDF_NO_TXT || GMD_PDF_EMPTY_BODY)) |
| #describe GMD_PDF_STOX_M4 PDF Stox spam |
| #score GMD_PDF_STOX_M4 2.95 |
| |
| # meta no body text along with automated pdf production. |
| #meta GMD_PDF_STOX_M5 ( __GMD_PDF_PRODUCERS && (__GMD_PDF_NO_TXT || GMD_PDF_EMPTY_BODY)) |
| #describe GMD_PDF_STOX_M5 PDF Stox Spam |
| #score GMD_PDF_STOX_M5 1.00 |
| |
| endif |