Added redact using insertion filter (#1196)

acceptanceTests/cypress.config.js

@@ -11,7 +11,6 @@ module.exports = defineConfig({
     testUrl: 'http://localhost:8899/',
     redactHeaderContent: 'User-Header[REDACTED]',
     redactBodyContent: '{ "User": "[REDACTED]" }',
-    regexMaskingBodyContent: '[REDACTED]',
     greenFilterColor: 'rgb(210, 250, 210)',
     redFilterColor: 'rgb(250, 214, 220)',
     bodyJsonClass: '.hljs',

acceptanceTests/cypress/e2e/tests/RegexMasking.js

-import {isValueExistsInElement} from "../testHelpers/TrafficHelper";
-
-it('Loading Mizu', function () {
-    cy.visit(Cypress.env('testUrl'));
-});
-
-isValueExistsInElement(true, Cypress.env('regexMaskingBodyContent'), Cypress.env('bodyJsonClass'));

acceptanceTests/tap_test.go

@@ -2,10 +2,8 @@ package acceptanceTests
 
 import (
 	"archive/zip"
-	"bytes"
 	"fmt"
 	"io/ioutil"
-	"net/http"
 	"os/exec"
 	"path"
 	"strings"
@@ -343,7 +341,7 @@ func TestTapRedact(t *testing.T) {
 
 	tapNamespace := GetDefaultTapNamespace()
 	tapCmdArgs = append(tapCmdArgs, tapNamespace...)
-	tapCmdArgs = append(tapCmdArgs, "--redact")
+	tapCmdArgs = append(tapCmdArgs, "--redact", "--set", "tap.redact-patterns.request-headers=User-Header", "--set", "tap.redact-patterns.request-body=User")
 
 	tapCmd := exec.Command(cliPath, tapCmdArgs...)
 	t.Logf("running command: %v", tapCmd.String())
@@ -429,60 +427,6 @@ func TestTapNoRedact(t *testing.T) {
 	RunCypressTests(t, "npx cypress run --spec  \"cypress/e2e/tests/NoRedact.js\"")
 }
 
-func TestTapRegexMasking(t *testing.T) {
-	if testing.Short() {
-		t.Skip("ignored acceptance test")
-	}
-
-	cliPath, cliPathErr := GetCliPath()
-	if cliPathErr != nil {
-		t.Errorf("failed to get cli path, err: %v", cliPathErr)
-		return
-	}
-
-	tapCmdArgs := GetDefaultTapCommandArgs()
-
-	tapNamespace := GetDefaultTapNamespace()
-	tapCmdArgs = append(tapCmdArgs, tapNamespace...)
-
-	tapCmdArgs = append(tapCmdArgs, "--redact")
-
-	tapCmdArgs = append(tapCmdArgs, "-r", "Mizu")
-
-	tapCmd := exec.Command(cliPath, tapCmdArgs...)
-	t.Logf("running command: %v", tapCmd.String())
-
-	t.Cleanup(func() {
-		if err := CleanupCommand(tapCmd); err != nil {
-			t.Logf("failed to cleanup tap command, err: %v", err)
-		}
-	})
-
-	if err := tapCmd.Start(); err != nil {
-		t.Errorf("failed to start tap command, err: %v", err)
-		return
-	}
-
-	apiServerUrl := GetApiServerUrl(DefaultApiServerPort)
-
-	if err := WaitTapPodsReady(apiServerUrl); err != nil {
-		t.Errorf("failed to start tap pods on time, err: %v", err)
-		return
-	}
-
-	proxyUrl := GetProxyUrl(DefaultNamespaceName, DefaultServiceName)
-	for i := 0; i < DefaultEntriesCount; i++ {
-		response, requestErr := http.Post(fmt.Sprintf("%v/post", proxyUrl), "text/plain", bytes.NewBufferString("Mizu"))
-		if _, requestErr = ExecuteHttpRequest(response, requestErr); requestErr != nil {
-			t.Errorf("failed to send proxy request, err: %v", requestErr)
-			return
-		}
-	}
-
-	RunCypressTests(t, "npx cypress run --spec \"cypress/e2e/tests/RegexMasking.js\"")
-
-}
-
 func TestTapIgnoredUserAgents(t *testing.T) {
 	if testing.Short() {
 		t.Skip("ignored acceptance test")

cli/cmd/tap.go

@@ -48,7 +48,6 @@ func init() {
 	tapCmd.Flags().Uint16P(configStructs.GuiPortTapName, "p", defaultTapConfig.GuiPort, "Provide a custom port for the web interface webserver")
 	tapCmd.Flags().StringSliceP(configStructs.NamespacesTapName, "n", defaultTapConfig.Namespaces, "Namespaces selector")
 	tapCmd.Flags().BoolP(configStructs.AllNamespacesTapName, "A", defaultTapConfig.AllNamespaces, "Tap all namespaces")
-	tapCmd.Flags().StringSliceP(configStructs.PlainTextFilterRegexesTapName, "r", defaultTapConfig.PlainTextFilterRegexes, "List of regex expressions that are used to filter matching values from text/plain http bodies")
 	tapCmd.Flags().Bool(configStructs.EnableRedactionTapName, defaultTapConfig.EnableRedaction, "Enables redaction of potentially sensitive request/response headers and body values")
 	tapCmd.Flags().String(configStructs.HumanMaxEntriesDBSizeTapName, defaultTapConfig.HumanMaxEntriesDBSize, "Override the default max entries db size")
 	tapCmd.Flags().String(configStructs.InsertionFilterName, defaultTapConfig.InsertionFilter, "Set the insertion filter. Accepts string or a file path.")

cli/cmd/tapRunner.go

@@ -230,23 +230,8 @@ func getErrorDisplayTextForK8sTapManagerError(err kubernetes.K8sTapManagerError)
 }
 
 func getMizuApiFilteringOptions() (*api.TrafficFilteringOptions, error) {
-	var compiledRegexSlice []*api.SerializableRegexp
-
-	if config.Config.Tap.PlainTextFilterRegexes != nil && len(config.Config.Tap.PlainTextFilterRegexes) > 0 {
-		compiledRegexSlice = make([]*api.SerializableRegexp, 0)
-		for _, regexStr := range config.Config.Tap.PlainTextFilterRegexes {
-			compiledRegex, err := api.CompileRegexToSerializableRegexp(regexStr)
-			if err != nil {
-				return nil, err
-			}
-			compiledRegexSlice = append(compiledRegexSlice, compiledRegex)
-		}
-	}
-
 	return &api.TrafficFilteringOptions{
-		PlainTextMaskingRegexes: compiledRegexSlice,
-		IgnoredUserAgents:       config.Config.Tap.IgnoredUserAgents,
-		EnableRedaction:        config.Config.Tap.EnableRedaction,
+		IgnoredUserAgents: config.Config.Tap.IgnoredUserAgents,
 	}, nil
 }
 

cli/config/configStructs/tapConfig.go

@@ -6,6 +6,7 @@ import (
 	"io/ioutil"
 	"os"
 	"regexp"
+	"strings"
 
 	"github.com/up9inc/mizu/cli/uiUtils"
 	"github.com/up9inc/mizu/shared"
@@ -15,38 +16,43 @@ import (
 )
 
 const (
-	GuiPortTapName                = "gui-port"
-	NamespacesTapName             = "namespaces"
-	AllNamespacesTapName          = "all-namespaces"
-	PlainTextFilterRegexesTapName = "regex-masking"
-	EnableRedactionTapName        = "redact"
-	HumanMaxEntriesDBSizeTapName  = "max-entries-db-size"
-	InsertionFilterName           = "insertion-filter"
-	DryRunTapName                 = "dry-run"
-	ServiceMeshName               = "service-mesh"
-	TlsName                       = "tls"
-	ProfilerName                  = "profiler"
-	MaxLiveStreamsName            = "max-live-streams"
+	GuiPortTapName               = "gui-port"
+	NamespacesTapName            = "namespaces"
+	AllNamespacesTapName         = "all-namespaces"
+	EnableRedactionTapName       = "redact"
+	HumanMaxEntriesDBSizeTapName = "max-entries-db-size"
+	InsertionFilterName          = "insertion-filter"
+	DryRunTapName                = "dry-run"
+	ServiceMeshName              = "service-mesh"
+	TlsName                      = "tls"
+	ProfilerName                 = "profiler"
+	MaxLiveStreamsName           = "max-live-streams"
 )
 
 type TapConfig struct {
-	PodRegexStr            string           `yaml:"regex" default:".*"`
-	GuiPort                uint16           `yaml:"gui-port" default:"8899"`
-	ProxyHost              string           `yaml:"proxy-host" default:"127.0.0.1"`
-	Namespaces             []string         `yaml:"namespaces"`
-	AllNamespaces          bool             `yaml:"all-namespaces" default:"false"`
-	PlainTextFilterRegexes []string         `yaml:"regex-masking"`
-	IgnoredUserAgents      []string         `yaml:"ignored-user-agents"`
-	EnableRedaction        bool             `yaml:"redact" default:"false"`
-	HumanMaxEntriesDBSize  string           `yaml:"max-entries-db-size" default:"200MB"`
-	InsertionFilter        string           `yaml:"insertion-filter" default:""`
-	DryRun                 bool             `yaml:"dry-run" default:"false"`
-	ApiServerResources     shared.Resources `yaml:"api-server-resources"`
-	TapperResources        shared.Resources `yaml:"tapper-resources"`
-	ServiceMesh            bool             `yaml:"service-mesh" default:"false"`
-	Tls                    bool             `yaml:"tls" default:"false"`
-	Profiler               bool             `yaml:"profiler" default:"false"`
-	MaxLiveStreams         int              `yaml:"max-live-streams" default:"500"`
+	PodRegexStr       string   `yaml:"regex" default:".*"`
+	GuiPort           uint16   `yaml:"gui-port" default:"8899"`
+	ProxyHost         string   `yaml:"proxy-host" default:"127.0.0.1"`
+	Namespaces        []string `yaml:"namespaces"`
+	AllNamespaces     bool     `yaml:"all-namespaces" default:"false"`
+	IgnoredUserAgents []string `yaml:"ignored-user-agents"`
+	EnableRedaction   bool     `yaml:"redact" default:"false"`
+	RedactPatterns    struct {
+		RequestHeaders     []string `yaml:"request-headers"`
+		ResponseHeaders    []string `yaml:"response-headers"`
+		RequestBody        []string `yaml:"request-body"`
+		ResponseBody       []string `yaml:"response-body"`
+		RequestQueryParams []string `yaml:"request-query-params"`
+	} `yaml:"redact-patterns"`
+	HumanMaxEntriesDBSize string           `yaml:"max-entries-db-size" default:"200MB"`
+	InsertionFilter       string           `yaml:"insertion-filter" default:""`
+	DryRun                bool             `yaml:"dry-run" default:"false"`
+	ApiServerResources    shared.Resources `yaml:"api-server-resources"`
+	TapperResources       shared.Resources `yaml:"tapper-resources"`
+	ServiceMesh           bool             `yaml:"service-mesh" default:"false"`
+	Tls                   bool             `yaml:"tls" default:"false"`
+	Profiler              bool             `yaml:"profiler" default:"false"`
+	MaxLiveStreams        int              `yaml:"max-live-streams" default:"500"`
 }
 
 func (config *TapConfig) PodRegex() *regexp.Regexp {
@@ -71,9 +77,48 @@ func (config *TapConfig) GetInsertionFilter() string {
 			}
 		}
 	}
+
+	redactFilter := getRedactFilter(config)
+	if insertionFilter != "" && redactFilter != "" {
+		return fmt.Sprintf("(%s) and (%s)", insertionFilter, redactFilter)
+	} else if insertionFilter == "" && redactFilter != "" {
+		return redactFilter
+	}
+
 	return insertionFilter
 }
 
+func getRedactFilter(config *TapConfig) string {
+	if !config.EnableRedaction {
+		return ""
+	}
+
+	var redactValues []string
+	for _, requestHeader := range config.RedactPatterns.RequestHeaders {
+		redactValues = append(redactValues, fmt.Sprintf("request.headers['%s']", requestHeader))
+	}
+	for _, responseHeader := range config.RedactPatterns.ResponseHeaders {
+		redactValues = append(redactValues, fmt.Sprintf("response.headers['%s']", responseHeader))
+	}
+
+	for _, requestBody := range config.RedactPatterns.RequestBody {
+		redactValues = append(redactValues, fmt.Sprintf("request.postData.text.json()...%s", requestBody))
+	}
+	for _, responseBody := range config.RedactPatterns.ResponseBody {
+		redactValues = append(redactValues, fmt.Sprintf("response.content.text.json()...%s", responseBody))
+	}
+
+	for _, requestQueryParams := range config.RedactPatterns.RequestQueryParams {
+		redactValues = append(redactValues, fmt.Sprintf("request.queryString['%s']", requestQueryParams))
+	}
+
+	if len(redactValues) == 0 {
+		return ""
+	}
+
+	return fmt.Sprintf("redact(\"%s\")", strings.Join(redactValues, "\",\""))
+}
+
 func (config *TapConfig) Validate() error {
 	_, compileErr := regexp.Compile(config.PodRegexStr)
 	if compileErr != nil {

performance_analysis/run_tapper_benchmark.sh

@@ -57,7 +57,7 @@ log "Writing output to $MIZU_BENCHMARK_OUTPUT_DIR"
 cd $MIZU_HOME || exit 1
 
 export HOST_MODE=0
-export SENSITIVE_DATA_FILTERING_OPTIONS='{"EnableRedaction": false}'
+export SENSITIVE_DATA_FILTERING_OPTIONS='{}'
 export MIZU_DEBUG_DISABLE_PCAP=false
 export MIZU_DEBUG_DISABLE_TCP_REASSEMBLY=false
 export MIZU_DEBUG_DISABLE_TCP_STREAM=false

tap/api/options.go

 package api
 
 type TrafficFilteringOptions struct {
-	IgnoredUserAgents       []string
-	PlainTextMaskingRegexes []*SerializableRegexp
-	EnableRedaction         bool
+	IgnoredUserAgents []string
 }

tap/extensions/http/handlers.go

@@ -18,10 +18,6 @@ func filterAndEmit(item *api.OutputChannelItem, emitter api.Emitter, options *ap
 		return
 	}
 
-	if options.EnableRedaction {
-		FilterSensitiveData(item, options)
-	}
-
 	replaceForwardedFor(item)
 
 	emitter.Emit(item)

tap/extensions/http/sensitive_data_cleaner.go

 package http
 
 import (
-	"bytes"
-	"encoding/json"
-	"encoding/xml"
-	"errors"
-	"fmt"
-	"io/ioutil"
 	"net/http"
-	"net/url"
 	"strings"
 
-	"github.com/beevik/etree"
 	"github.com/up9inc/mizu/tap/api"
 )
 
-const maskedFieldPlaceholderValue = "[REDACTED]"
 const userAgent = "user-agent"
 
-//these values MUST be all lower case and contain no `-` or `_` characters
-var personallyIdentifiableDataFields = []string{"token", "authorization", "authentication", "cookie", "userid", "password",
-	"username", "user", "key", "passcode", "pass", "auth", "authtoken", "jwt",
-	"bearer", "clientid", "clientsecret", "redirecturi", "phonenumber",
-	"zip", "zipcode", "address", "country", "firstname", "lastname",
-	"middlename", "fname", "lname", "birthdate"}
-
 func IsIgnoredUserAgent(item *api.OutputChannelItem, options *api.TrafficFilteringOptions) bool {
 	if item.Protocol.Name != "http" {
 		return false
@@ -48,192 +32,3 @@ func IsIgnoredUserAgent(item *api.OutputChannelItem, options *api.TrafficFilteri
 
 	return false
 }
-
-func FilterSensitiveData(item *api.OutputChannelItem, options *api.TrafficFilteringOptions) {
-	request := item.Pair.Request.Payload.(HTTPPayload).Data.(*http.Request)
-	response := item.Pair.Response.Payload.(HTTPPayload).Data.(*http.Response)
-
-	filterHeaders(&request.Header)
-	filterHeaders(&response.Header)
-	filterUrl(request.URL)
-	filterRequestBody(request, options)
-	filterResponseBody(response, options)
-}
-
-func filterRequestBody(request *http.Request, options *api.TrafficFilteringOptions) {
-	contenType := getContentTypeHeaderValue(request.Header)
-	body, err := ioutil.ReadAll(request.Body)
-	if err != nil {
-		return
-	}
-	filteredBody, err := filterHttpBody(body, contenType, options)
-	if err == nil {
-		request.Body = ioutil.NopCloser(bytes.NewBuffer(filteredBody))
-	} else {
-		request.Body = ioutil.NopCloser(bytes.NewBuffer(body))
-	}
-}
-
-func filterResponseBody(response *http.Response, options *api.TrafficFilteringOptions) {
-	contentType := getContentTypeHeaderValue(response.Header)
-	body, err := ioutil.ReadAll(response.Body)
-	if err != nil {
-		return
-	}
-	filteredBody, err := filterHttpBody(body, contentType, options)
-	if err == nil {
-		response.Body = ioutil.NopCloser(bytes.NewBuffer(filteredBody))
-	} else {
-		response.Body = ioutil.NopCloser(bytes.NewBuffer(body))
-	}
-}
-
-func filterHeaders(headers *http.Header) {
-	for key := range *headers {
-		if strings.ToLower(key) == userAgent {
-			continue
-		}
-
-		if strings.ToLower(key) == "cookie" {
-			headers.Del(key)
-		} else if isFieldNameSensitive(key) {
-			headers.Set(key, maskedFieldPlaceholderValue)
-		}
-	}
-}
-
-func getContentTypeHeaderValue(headers http.Header) string {
-	for key := range headers {
-		if strings.ToLower(key) == "content-type" {
-			return headers.Get(key)
-		}
-	}
-	return ""
-}
-
-func isFieldNameSensitive(fieldName string) bool {
-	if fieldName == ":authority" {
-		return false
-	}
-
-	name := strings.ToLower(fieldName)
-	name = strings.ReplaceAll(name, "_", "")
-	name = strings.ReplaceAll(name, "-", "")
-	name = strings.ReplaceAll(name, " ", "")
-
-	for _, sensitiveField := range personallyIdentifiableDataFields {
-		if strings.Contains(name, sensitiveField) {
-			return true
-		}
-	}
-
-	return false
-}
-
-func filterHttpBody(bytes []byte, contentType string, options *api.TrafficFilteringOptions) ([]byte, error) {
-	mimeType := strings.Split(contentType, ";")[0]
-	switch strings.ToLower(mimeType) {
-	case "application/json":
-		return filterJsonBody(bytes)
-	case "text/html":
-		fallthrough
-	case "application/xhtml+xml":
-		fallthrough
-	case "text/xml":
-		fallthrough
-	case "application/xml":
-		return filterXmlEtree(bytes)
-	case "text/plain":
-		if options != nil && options.PlainTextMaskingRegexes != nil {
-			return filterPlainText(bytes, options), nil
-		}
-	}
-	return bytes, nil
-}
-
-func filterPlainText(bytes []byte, options *api.TrafficFilteringOptions) []byte {
-	for _, regex := range options.PlainTextMaskingRegexes {
-		bytes = regex.ReplaceAll(bytes, []byte(maskedFieldPlaceholderValue))
-	}
-	return bytes
-}
-
-func filterXmlEtree(bytes []byte) ([]byte, error) {
-	if !IsValidXML(bytes) {
-		return nil, errors.New("Invalid XML")
-	}
-	xmlDoc := etree.NewDocument()
-	err := xmlDoc.ReadFromBytes(bytes)
-	if err != nil {
-		return nil, err
-	} else {
-		filterXmlElement(xmlDoc.Root())
-	}
-	return xmlDoc.WriteToBytes()
-}
-
-func IsValidXML(data []byte) bool {
-	return xml.Unmarshal(data, new(interface{})) == nil
-}
-
-func filterXmlElement(element *etree.Element) {
-	for i, attribute := range element.Attr {
-		if isFieldNameSensitive(attribute.Key) {
-			element.Attr[i].Value = maskedFieldPlaceholderValue
-		}
-	}
-	if element.ChildElements() == nil || len(element.ChildElements()) == 0 {
-		if isFieldNameSensitive(element.Tag) {
-			element.SetText(maskedFieldPlaceholderValue)
-		}
-	} else {
-		for _, element := range element.ChildElements() {
-			filterXmlElement(element)
-		}
-	}
-}
-
-func filterJsonBody(bytes []byte) ([]byte, error) {
-	var bodyJsonMap map[string]interface{}
-	err := json.Unmarshal(bytes, &bodyJsonMap)
-	if err != nil {
-		return nil, err
-	}
-	filterJsonMap(bodyJsonMap)
-	return json.Marshal(bodyJsonMap)
-}
-
-func filterJsonMap(jsonMap map[string]interface{}) {
-	for key, value := range jsonMap {
-		// Do not replace nil values with maskedFieldPlaceholderValue
-		if value == nil {
-			continue
-		}
-
-		nestedMap, isNested := value.(map[string]interface{})
-		if isNested {
-			filterJsonMap(nestedMap)
-		} else {
-			if isFieldNameSensitive(key) {
-				jsonMap[key] = maskedFieldPlaceholderValue
-			}
-		}
-	}
-}
-
-func filterUrl(url *url.URL) {
-	if len(url.RawQuery) > 0 {
-		newQueryArgs := make([]string, 0)
-		for urlQueryParamName, urlQueryParamValues := range url.Query() {
-			newValues := urlQueryParamValues
-			if isFieldNameSensitive(urlQueryParamName) {
-				newValues = []string{maskedFieldPlaceholderValue}
-			}
-			for _, paramValue := range newValues {
-				newQueryArgs = append(newQueryArgs, fmt.Sprintf("%s=%s", urlQueryParamName, paramValue))
-			}
-		}
-
-		url.RawQuery = strings.Join(newQueryArgs, "&")
-	}
-}