From c2317f7d0550c3f4c7fa10e18f0c3094ec6117e7 Mon Sep 17 00:00:00 2001 From: Mingfei Shao Date: Thu, 14 Nov 2024 13:49:53 -0600 Subject: [PATCH] add customized modsec config for heal envs --- .secrets.baseline | 45 +-- .../manifests/modsec/modsecurity.conf | 269 ++++++++++++++++++ .../manifests/modsec/modsecurity.conf | 269 ++++++++++++++++++ 3 files changed, 539 insertions(+), 44 deletions(-) create mode 100644 healdata.org/manifests/modsec/modsecurity.conf create mode 100644 preprod.healdata.org/manifests/modsec/modsecurity.conf diff --git a/.secrets.baseline b/.secrets.baseline index 74037211e..ce83d86cc 100644 --- a/.secrets.baseline +++ b/.secrets.baseline @@ -75,10 +75,6 @@ { "path": "detect_secrets.filters.allowlist.is_line_allowlisted" }, - { - "path": "detect_secrets.filters.common.is_baseline_file", - "filename": ".secrets.baseline" - }, { "path": "detect_secrets.filters.common.is_ignored_due_to_verification_policies", "min_level": 2 @@ -171,22 +167,6 @@ "line_number": 8 } ], - "brh.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html": [ - { - "type": "AWS Access Key", - "filename": "brh.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html", - "hashed_secret": "49e961282798df9f7b70aa6a00bd9d2f65d820f8", - "is_verified": false, - "line_number": 14908 - }, - { - "type": "AWS Access Key", - "filename": "brh.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html", - "hashed_secret": "7438dcef879f4f35710bf2d1c682b4aa4c022552", - "is_verified": false, - "line_number": 14912 - } - ], "brh.data-commons.org/manifests/hatchery/hatchery.json": [ { "type": "Base64 High Entropy String", @@ -246,22 +226,6 @@ "line_number": 8 } ], - "brhstaging.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html": [ - { - "type": "AWS Access Key", - "filename": "brhstaging.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html", - "hashed_secret": "49e961282798df9f7b70aa6a00bd9d2f65d820f8", - "is_verified": false, - "line_number": 14908 - }, - { - "type": "AWS Access Key", - "filename": "brhstaging.data-commons.org/dashboard/Public/notebooks/canine_datacommons_fastq_reader.html", - "hashed_secret": "7438dcef879f4f35710bf2d1c682b4aa4c022552", - "is_verified": false, - "line_number": 14912 - } - ], "chicagoland.pandemicresponsecommons.org/dashboard/Public/index.html": [ { "type": "Base64 High Entropy String", @@ -285,13 +249,6 @@ "hashed_secret": "b5060a86e648e404a56667073dee3976689b4f0f", "is_verified": false, "line_number": 8 - }, - { - "type": "AWS Access Key", - "filename": "chicagoland.pandemicresponsecommons.org/dashboard/Public/notebooks/3D_Protein_Vis.html", - "hashed_secret": "8d66e53859e4b4b808385d6a3ef561b7971fa564", - "is_verified": false, - "line_number": 13396 } ], "chicagoland.pandemicresponsecommons.org/dashboard/Public/notebooks/3D_Protein_Vis_7D4F_view.html": [ @@ -9579,5 +9536,5 @@ } ] }, - "generated_at": "2024-11-12T19:58:12Z" + "generated_at": "2024-11-14T19:27:24Z" } diff --git a/healdata.org/manifests/modsec/modsecurity.conf b/healdata.org/manifests/modsec/modsecurity.conf new file mode 100644 index 000000000..73bf17ccf --- /dev/null +++ b/healdata.org/manifests/modsec/modsecurity.conf @@ -0,0 +1,269 @@ +# Copied from https://github.com/SpiderLabs/ModSecurity v3 modsecurity.conf-recommended +# See https://github.com/SpiderLabs/owasp-modsecurity-crs +# +# -- Rule engine initialization ---------------------------------------------- + +# Enable ModSecurity, attaching it to every transaction. Use detection +# only to start with, because that minimises the chances of post-installation +# disruption. +# +#SecRuleEngine DetectionOnly +SecRuleEngine On + + +# -- Request body handling --------------------------------------------------- + +# Allow ModSecurity to access request bodies. If you don't, ModSecurity +# won't be able to see any POST parameters, which opens a large security +# hole for attackers to exploit. +# +SecRequestBodyAccess On + + +# Enable XML request body parser. +# Initiate XML Processor in case of xml content-type +# +SecRule REQUEST_HEADERS:Content-Type "(?:application(?:/soap\+|/)|text/)xml" \ + "id:'200000',phase:1,t:none,t:lowercase,pass,nolog,ctl:requestBodyProcessor=XML" + +# Enable JSON request body parser. +# Initiate JSON Processor in case of JSON content-type; change accordingly +# if your application does not use 'application/json' +# +SecRule REQUEST_HEADERS:Content-Type "application/json" \ + "id:'200001',phase:1,t:none,t:lowercase,pass,nolog,ctl:requestBodyProcessor=JSON" + +# Maximum request body size we will accept for buffering. If you support +# file uploads then the value given on the first line has to be as large +# as the largest file you are willing to accept. The second value refers +# to the size of data, with files excluded. You want to keep that value as +# low as practical. +# +SecRequestBodyLimit 524288000 +# Set this to 5MB to accomodate some large MDS requests +SecRequestBodyNoFilesLimit 5242880 + +# What do do if the request body size is above our configured limit. +# Keep in mind that this setting will automatically be set to ProcessPartial +# when SecRuleEngine is set to DetectionOnly mode in order to minimize +# disruptions when initially deploying ModSecurity. +# +SecRequestBodyLimitAction ProcessPartial + +# Verify that we've correctly processed the request body. +# As a rule of thumb, when failing to process a request body +# you should reject the request (when deployed in blocking mode) +# or log a high-severity alert (when deployed in detection-only mode). +# +SecRule REQBODY_ERROR "!@eq 0" \ +"id:'200002', phase:2,t:none,log,deny,status:400,msg:'Failed to parse request body.',logdata:'%{reqbody_error_msg}',severity:2" + +# By default be strict with what we accept in the multipart/form-data +# request body. If the rule below proves to be too strict for your +# environment consider changing it to detection-only. You are encouraged +# _not_ to remove it altogether. +# +SecRule MULTIPART_STRICT_ERROR "!@eq 0" \ +"id:'200003',phase:2,t:none,log,deny,status:400, \ +msg:'Multipart request body failed strict validation: \ +PE %{REQBODY_PROCESSOR_ERROR}, \ +BQ %{MULTIPART_BOUNDARY_QUOTED}, \ +BW %{MULTIPART_BOUNDARY_WHITESPACE}, \ +DB %{MULTIPART_DATA_BEFORE}, \ +DA %{MULTIPART_DATA_AFTER}, \ +HF %{MULTIPART_HEADER_FOLDING}, \ +LF %{MULTIPART_LF_LINE}, \ +SM %{MULTIPART_MISSING_SEMICOLON}, \ +IQ %{MULTIPART_INVALID_QUOTING}, \ +IP %{MULTIPART_INVALID_PART}, \ +IH %{MULTIPART_INVALID_HEADER_FOLDING}, \ +FL %{MULTIPART_FILE_LIMIT_EXCEEDED}'" + +# Did we see anything that might be a boundary? +# +# Here is a short description about the ModSecurity Multipart parser: the +# parser returns with value 0, if all "boundary-like" line matches with +# the boundary string which given in MIME header. In any other cases it returns +# with different value, eg. 1 or 2. +# +# The RFC 1341 descript the multipart content-type and its syntax must contains +# only three mandatory lines (above the content): +# * Content-Type: multipart/mixed; boundary=BOUNDARY_STRING +# * --BOUNDARY_STRING +# * --BOUNDARY_STRING-- +# +# First line indicates, that this is a multipart content, second shows that +# here starts a part of the multipart content, third shows the end of content. +# +# If there are any other lines, which starts with "--", then it should be +# another boundary id - or not. +# +# After 3.0.3, there are two kinds of types of boundary errors: strict and permissive. +# +# If multipart content contains the three necessary lines with correct order, but +# there are one or more lines with "--", then parser returns with value 2 (non-zero). +# +# If some of the necessary lines (usually the start or end) misses, or the order +# is wrong, then parser returns with value 1 (also a non-zero). +# +# You can choose, which one is what you need. The example below contains the +# 'strict' mode, which means if there are any lines with start of "--", then +# ModSecurity blocked the content. But the next, commented example contains +# the 'permissive' mode, then you check only if the necessary lines exists in +# correct order. Whit this, you can enable to upload PEM files (eg "----BEGIN.."), +# or other text files, which contains eg. HTTP headers. +# +# The difference is only the operator - in strict mode (first) the content blocked +# in case of any non-zero value. In permissive mode (second, commented) the +# content blocked only if the value is explicit 1. If it 0 or 2, the content will +# allowed. +# + +# +# See #1747 and #1924 for further information on the possible values for +# MULTIPART_UNMATCHED_BOUNDARY. +# +SecRule MULTIPART_UNMATCHED_BOUNDARY "@eq 1" \ + "id:'200004',phase:2,t:none,log,deny,msg:'Multipart parser detected a possible unmatched boundary.'" + + +# PCRE Tuning +# We want to avoid a potential RegEx DoS condition +# +SecPcreMatchLimit 1000 +SecPcreMatchLimitRecursion 1000 + +# Some internal errors will set flags in TX and we will need to look for these. +# All of these are prefixed with "MSC_". The following flags currently exist: +# +# MSC_PCRE_LIMITS_EXCEEDED: PCRE match limits were exceeded. +# +SecRule TX:/^MSC_/ "!@streq 0" \ + "id:'200005',phase:2,t:none,deny,msg:'ModSecurity internal error flagged: %{MATCHED_VAR_NAME}'" + + +# -- Response body handling -------------------------------------------------- + +# Allow ModSecurity to access response bodies. +# You should have this directive enabled in order to identify errors +# and data leakage issues. +# +# Do keep in mind that enabling this directive does increases both +# memory consumption and response latency. +# +SecResponseBodyAccess On + +# Which response MIME types do you want to inspect? You should adjust the +# configuration below to catch documents but avoid static files +# (e.g., images and archives). +# +SecResponseBodyMimeType text/plain text/html text/xml + +# Buffer response bodies of up to 512 KB in length. +SecResponseBodyLimit 524288 + +# What happens when we encounter a response body larger than the configured +# limit? By default, we process what we have and let the rest through. +# That's somewhat less secure, but does not break any legitimate pages. +# +SecResponseBodyLimitAction ProcessPartial + + +# -- Filesystem configuration ------------------------------------------------ + +# The location where ModSecurity stores temporary files (for example, when +# it needs to handle a file upload that is larger than the configured limit). +# +# This default setting is chosen due to all systems have /tmp available however, +# this is less than ideal. It is recommended that you specify a location that's private. +# +SecTmpDir /tmp/ + +# The location where ModSecurity will keep its persistent data. This default setting +# is chosen due to all systems have /tmp available however, it +# too should be updated to a place that other users can't access. +# +SecDataDir /tmp/ + + +# -- File uploads handling configuration ------------------------------------- + +# The location where ModSecurity stores intercepted uploaded files. This +# location must be private to ModSecurity. You don't want other users on +# the server to access the files, do you? +# +#SecUploadDir /opt/modsecurity/var/upload/ + +# By default, only keep the files that were determined to be unusual +# in some way (by an external inspection script). For this to work you +# will also need at least one file inspection rule. +# +#SecUploadKeepFiles RelevantOnly + +# Uploaded files are by default created with permissions that do not allow +# any other user to access them. You may need to relax that if you want to +# interface ModSecurity to an external program (e.g., an anti-virus). +# +#SecUploadFileMode 0600 + + +# -- Debug log configuration ------------------------------------------------- + +# The default debug log configuration is to duplicate the error, warning +# and notice messages from the error log. +# +#SecDebugLog /opt/modsecurity/var/log/debug.log +#SecDebugLogLevel 3 + + +# -- Audit log configuration ------------------------------------------------- +# See https://www.nginx.com/blog/modsecurity-logging-and-debugging/ + +# Log the transactions that are marked by a rule, as well as those that +# trigger a server error (determined by a 5xx or 4xx, excluding 404, +# level response status codes). +# +SecAuditEngine RelevantOnly +SecAuditLogRelevantStatus "^(?:5|4(?!04))" + +# Log everything we know about a transaction. +SecAuditLogParts ABIJDEFHZ + +# Use a single file for logging. This is much easier to look at, but +# assumes that you will use the audit log only ocassionally. +# +SecAuditLogType Serial +SecAuditLog /var/log/modsec_audit.log +SecAuditLogFormat JSON + +# Specify the path for concurrent audit logging. +#SecAuditLogStorageDir /opt/modsecurity/var/audit/ + + +# -- Miscellaneous ----------------------------------------------------------- + +# Use the most commonly used application/x-www-form-urlencoded parameter +# separator. There's probably only one application somewhere that uses +# something else so don't expect to change this value. +# +SecArgumentSeparator & + +# Settle on version 0 (zero) cookies, as that is what most applications +# use. Using an incorrect cookie version may open your installation to +# evasion attacks (against the rules that examine named cookies). +# +SecCookieFormat 0 + +# Specify your Unicode Code Point. +# This mapping is used by the t:urlDecodeUni transformation function +# to properly map encoded data to your language. Properly setting +# these directives helps to reduce false positives and negatives. +# +SecUnicodeMapFile unicode.mapping 20127 + +# Improve the quality of ModSecurity by sharing information about your +# current ModSecurity version and dependencies versions. +# The following information will be shared: ModSecurity version, +# Web Server version, APR version, PCRE version, Lua version, Libxml2 +# version, Anonymous unique id for host. +SecStatusEngine On \ No newline at end of file diff --git a/preprod.healdata.org/manifests/modsec/modsecurity.conf b/preprod.healdata.org/manifests/modsec/modsecurity.conf new file mode 100644 index 000000000..73bf17ccf --- /dev/null +++ b/preprod.healdata.org/manifests/modsec/modsecurity.conf @@ -0,0 +1,269 @@ +# Copied from https://github.com/SpiderLabs/ModSecurity v3 modsecurity.conf-recommended +# See https://github.com/SpiderLabs/owasp-modsecurity-crs +# +# -- Rule engine initialization ---------------------------------------------- + +# Enable ModSecurity, attaching it to every transaction. Use detection +# only to start with, because that minimises the chances of post-installation +# disruption. +# +#SecRuleEngine DetectionOnly +SecRuleEngine On + + +# -- Request body handling --------------------------------------------------- + +# Allow ModSecurity to access request bodies. If you don't, ModSecurity +# won't be able to see any POST parameters, which opens a large security +# hole for attackers to exploit. +# +SecRequestBodyAccess On + + +# Enable XML request body parser. +# Initiate XML Processor in case of xml content-type +# +SecRule REQUEST_HEADERS:Content-Type "(?:application(?:/soap\+|/)|text/)xml" \ + "id:'200000',phase:1,t:none,t:lowercase,pass,nolog,ctl:requestBodyProcessor=XML" + +# Enable JSON request body parser. +# Initiate JSON Processor in case of JSON content-type; change accordingly +# if your application does not use 'application/json' +# +SecRule REQUEST_HEADERS:Content-Type "application/json" \ + "id:'200001',phase:1,t:none,t:lowercase,pass,nolog,ctl:requestBodyProcessor=JSON" + +# Maximum request body size we will accept for buffering. If you support +# file uploads then the value given on the first line has to be as large +# as the largest file you are willing to accept. The second value refers +# to the size of data, with files excluded. You want to keep that value as +# low as practical. +# +SecRequestBodyLimit 524288000 +# Set this to 5MB to accomodate some large MDS requests +SecRequestBodyNoFilesLimit 5242880 + +# What do do if the request body size is above our configured limit. +# Keep in mind that this setting will automatically be set to ProcessPartial +# when SecRuleEngine is set to DetectionOnly mode in order to minimize +# disruptions when initially deploying ModSecurity. +# +SecRequestBodyLimitAction ProcessPartial + +# Verify that we've correctly processed the request body. +# As a rule of thumb, when failing to process a request body +# you should reject the request (when deployed in blocking mode) +# or log a high-severity alert (when deployed in detection-only mode). +# +SecRule REQBODY_ERROR "!@eq 0" \ +"id:'200002', phase:2,t:none,log,deny,status:400,msg:'Failed to parse request body.',logdata:'%{reqbody_error_msg}',severity:2" + +# By default be strict with what we accept in the multipart/form-data +# request body. If the rule below proves to be too strict for your +# environment consider changing it to detection-only. You are encouraged +# _not_ to remove it altogether. +# +SecRule MULTIPART_STRICT_ERROR "!@eq 0" \ +"id:'200003',phase:2,t:none,log,deny,status:400, \ +msg:'Multipart request body failed strict validation: \ +PE %{REQBODY_PROCESSOR_ERROR}, \ +BQ %{MULTIPART_BOUNDARY_QUOTED}, \ +BW %{MULTIPART_BOUNDARY_WHITESPACE}, \ +DB %{MULTIPART_DATA_BEFORE}, \ +DA %{MULTIPART_DATA_AFTER}, \ +HF %{MULTIPART_HEADER_FOLDING}, \ +LF %{MULTIPART_LF_LINE}, \ +SM %{MULTIPART_MISSING_SEMICOLON}, \ +IQ %{MULTIPART_INVALID_QUOTING}, \ +IP %{MULTIPART_INVALID_PART}, \ +IH %{MULTIPART_INVALID_HEADER_FOLDING}, \ +FL %{MULTIPART_FILE_LIMIT_EXCEEDED}'" + +# Did we see anything that might be a boundary? +# +# Here is a short description about the ModSecurity Multipart parser: the +# parser returns with value 0, if all "boundary-like" line matches with +# the boundary string which given in MIME header. In any other cases it returns +# with different value, eg. 1 or 2. +# +# The RFC 1341 descript the multipart content-type and its syntax must contains +# only three mandatory lines (above the content): +# * Content-Type: multipart/mixed; boundary=BOUNDARY_STRING +# * --BOUNDARY_STRING +# * --BOUNDARY_STRING-- +# +# First line indicates, that this is a multipart content, second shows that +# here starts a part of the multipart content, third shows the end of content. +# +# If there are any other lines, which starts with "--", then it should be +# another boundary id - or not. +# +# After 3.0.3, there are two kinds of types of boundary errors: strict and permissive. +# +# If multipart content contains the three necessary lines with correct order, but +# there are one or more lines with "--", then parser returns with value 2 (non-zero). +# +# If some of the necessary lines (usually the start or end) misses, or the order +# is wrong, then parser returns with value 1 (also a non-zero). +# +# You can choose, which one is what you need. The example below contains the +# 'strict' mode, which means if there are any lines with start of "--", then +# ModSecurity blocked the content. But the next, commented example contains +# the 'permissive' mode, then you check only if the necessary lines exists in +# correct order. Whit this, you can enable to upload PEM files (eg "----BEGIN.."), +# or other text files, which contains eg. HTTP headers. +# +# The difference is only the operator - in strict mode (first) the content blocked +# in case of any non-zero value. In permissive mode (second, commented) the +# content blocked only if the value is explicit 1. If it 0 or 2, the content will +# allowed. +# + +# +# See #1747 and #1924 for further information on the possible values for +# MULTIPART_UNMATCHED_BOUNDARY. +# +SecRule MULTIPART_UNMATCHED_BOUNDARY "@eq 1" \ + "id:'200004',phase:2,t:none,log,deny,msg:'Multipart parser detected a possible unmatched boundary.'" + + +# PCRE Tuning +# We want to avoid a potential RegEx DoS condition +# +SecPcreMatchLimit 1000 +SecPcreMatchLimitRecursion 1000 + +# Some internal errors will set flags in TX and we will need to look for these. +# All of these are prefixed with "MSC_". The following flags currently exist: +# +# MSC_PCRE_LIMITS_EXCEEDED: PCRE match limits were exceeded. +# +SecRule TX:/^MSC_/ "!@streq 0" \ + "id:'200005',phase:2,t:none,deny,msg:'ModSecurity internal error flagged: %{MATCHED_VAR_NAME}'" + + +# -- Response body handling -------------------------------------------------- + +# Allow ModSecurity to access response bodies. +# You should have this directive enabled in order to identify errors +# and data leakage issues. +# +# Do keep in mind that enabling this directive does increases both +# memory consumption and response latency. +# +SecResponseBodyAccess On + +# Which response MIME types do you want to inspect? You should adjust the +# configuration below to catch documents but avoid static files +# (e.g., images and archives). +# +SecResponseBodyMimeType text/plain text/html text/xml + +# Buffer response bodies of up to 512 KB in length. +SecResponseBodyLimit 524288 + +# What happens when we encounter a response body larger than the configured +# limit? By default, we process what we have and let the rest through. +# That's somewhat less secure, but does not break any legitimate pages. +# +SecResponseBodyLimitAction ProcessPartial + + +# -- Filesystem configuration ------------------------------------------------ + +# The location where ModSecurity stores temporary files (for example, when +# it needs to handle a file upload that is larger than the configured limit). +# +# This default setting is chosen due to all systems have /tmp available however, +# this is less than ideal. It is recommended that you specify a location that's private. +# +SecTmpDir /tmp/ + +# The location where ModSecurity will keep its persistent data. This default setting +# is chosen due to all systems have /tmp available however, it +# too should be updated to a place that other users can't access. +# +SecDataDir /tmp/ + + +# -- File uploads handling configuration ------------------------------------- + +# The location where ModSecurity stores intercepted uploaded files. This +# location must be private to ModSecurity. You don't want other users on +# the server to access the files, do you? +# +#SecUploadDir /opt/modsecurity/var/upload/ + +# By default, only keep the files that were determined to be unusual +# in some way (by an external inspection script). For this to work you +# will also need at least one file inspection rule. +# +#SecUploadKeepFiles RelevantOnly + +# Uploaded files are by default created with permissions that do not allow +# any other user to access them. You may need to relax that if you want to +# interface ModSecurity to an external program (e.g., an anti-virus). +# +#SecUploadFileMode 0600 + + +# -- Debug log configuration ------------------------------------------------- + +# The default debug log configuration is to duplicate the error, warning +# and notice messages from the error log. +# +#SecDebugLog /opt/modsecurity/var/log/debug.log +#SecDebugLogLevel 3 + + +# -- Audit log configuration ------------------------------------------------- +# See https://www.nginx.com/blog/modsecurity-logging-and-debugging/ + +# Log the transactions that are marked by a rule, as well as those that +# trigger a server error (determined by a 5xx or 4xx, excluding 404, +# level response status codes). +# +SecAuditEngine RelevantOnly +SecAuditLogRelevantStatus "^(?:5|4(?!04))" + +# Log everything we know about a transaction. +SecAuditLogParts ABIJDEFHZ + +# Use a single file for logging. This is much easier to look at, but +# assumes that you will use the audit log only ocassionally. +# +SecAuditLogType Serial +SecAuditLog /var/log/modsec_audit.log +SecAuditLogFormat JSON + +# Specify the path for concurrent audit logging. +#SecAuditLogStorageDir /opt/modsecurity/var/audit/ + + +# -- Miscellaneous ----------------------------------------------------------- + +# Use the most commonly used application/x-www-form-urlencoded parameter +# separator. There's probably only one application somewhere that uses +# something else so don't expect to change this value. +# +SecArgumentSeparator & + +# Settle on version 0 (zero) cookies, as that is what most applications +# use. Using an incorrect cookie version may open your installation to +# evasion attacks (against the rules that examine named cookies). +# +SecCookieFormat 0 + +# Specify your Unicode Code Point. +# This mapping is used by the t:urlDecodeUni transformation function +# to properly map encoded data to your language. Properly setting +# these directives helps to reduce false positives and negatives. +# +SecUnicodeMapFile unicode.mapping 20127 + +# Improve the quality of ModSecurity by sharing information about your +# current ModSecurity version and dependencies versions. +# The following information will be shared: ModSecurity version, +# Web Server version, APR version, PCRE version, Lua version, Libxml2 +# version, Anonymous unique id for host. +SecStatusEngine On \ No newline at end of file