implement redaction filters

api/v1/tetragon/events.proto

@@ -83,6 +83,13 @@ message CapFilterSet {
 	repeated CapabilitiesType none = 4;
 }
 
+message RedactionFilter {
+    // Match events that the redaction filter will apply to.
+    repeated Filter match = 1;
+    // Regular expressions to use for redaction. Strings inside capture groups are redacted.
+    repeated string redact = 2;
+}
+
 // Determines the behavior of a field filter
 enum FieldFilterAction {
     INCLUDE = 0;

cmd/tetragon/main.go

@@ -108,6 +108,11 @@ func getFieldFilters() ([]*tetragon.FieldFilter, error) {
 	return filters, nil
 }
 
+func getRedactionFilters() (fieldfilters.RedactionFilterList, error) {
+	redactionFilters := viper.GetString(option.KeyRedactionFilters)
+	return fieldfilters.ParseRedactionFilterList(redactionFilters)
+}
+
 // Save daemon information so it is used by client cli but
 // also by bugtool
 func saveInitInfo() error {
@@ -401,11 +406,18 @@ func tetragonExecute() error {
 
 	hookRunner := rthooks.GlobalRunner().WithWatcher(k8sWatcher)
 
+	redactionFilters, err := getRedactionFilters()
+	if err != nil {
+		return err
+	}
+	log.WithFields(logrus.Fields{"redactionFilters": redactionFilters}).Info("Configured redaction filters")
+
 	pm, err := tetragonGrpc.NewProcessManager(
 		ctx,
 		&cleanupWg,
 		observer.GetSensorManager(),
-		hookRunner)
+		hookRunner,
+		redactionFilters)
 	if err != nil {
 		return err
 	}
@@ -705,7 +717,7 @@ func startExporter(ctx context.Context, server *server.Server) error {
 		}
 	}
 	req := tetragon.GetEventsRequest{AllowList: allowList, DenyList: denyList, AggregationOptions: aggregationOptions, FieldFilters: fieldFilters}
-	log.WithFields(logrus.Fields{"fieldFilters": fieldFilters}).Debug("Configured field filters")
+	log.WithFields(logrus.Fields{"fieldFilters": fieldFilters}).Info("Configured field filters")
 	log.WithFields(logrus.Fields{"logger": writer, "request": &req}).Info("Starting JSON exporter")
 	exporter := exporter.NewExporter(ctx, &req, server, encoder, writer, rateLimiter)
 	return exporter.Start()

docs/content/en/docs/concepts/events.md

@@ -197,6 +197,49 @@ only `exec_id` and `parent_exec_id` in all event types except for
 {"fields":"process.exec_id,process.parent_exec_id", "event_set": ["PROCESS_EXEC"], "invert_event_set": true, "action": "INCLUDE"}
 ```
 
+#### Redacting Sensitive Information
+
+Since Tetragon traces the entire system, event exports might sometimes contain
+sensitive information (for example, a secret passed via a command line argument
+to a process). To prevent this information from being exfiltrated via Tetragon
+JSON export, Tetragon provides a mechanism called Redaction Filters which can be
+used to select events and string patterns to redact. These filters are written
+in JSON and passed to the Tetragon agent via the `--redaction-filters` command
+line flag or the `redactionFilters` Helm value.
+
+To perform redactions, redaction filters define regular expressions in the
+`redact` field. Any capture groups in these regular expressions are redacted and
+replaced with `"*****"`.
+
+{{< warning >}}
+When writing regular expressions in JSON, it is important to escape backslash
+characters. For instance `\Wpasswd\W?` would be written as `{"redact": "\\Wpasswd\\W?"}`.
+{{< /warning >}}
+
+Redaction filters select events using the `match` field, which contains one or
+more filters (these filters are defined the same way as export filters). If no
+match filter is defined, all events are selected.
+
+As a concrete example, the following will redact all passwords passed to
+processes with the `"--password"` argument:
+
+```json
+{"redact": ["--password(?:\\s+|=)(\\S*)"]}
+```
+
+Now, an event that contains the string `"--password=foo"` would have that string
+replaced with `"--password=*****"`.
+
+Suppose we also see some passwords passed via the -p shorthand for a specific binary, foo.
+We can also redact these as follows:
+
+```json
+{"match": [{"binary_regex": "(?:^|/)foo$"}], "redact": ["-p(?:\\s+|=)(\\S*)"]}
+```
+
+With both of the above redaction filters in place, we are now redacting all
+password arguments.
+
 ### `tetra` CLI
 
 A second way is to use the [`tetra`](https://github.com/cilium/tetragon/tree/main/cmd/tetra) CLI. This
@@ -245,4 +288,4 @@ An example gRPC endpoint is the Tetra CLI when its not piped JSON output directl
 
 ```shell
  kubectl exec -ti -n kube-system ds/tetragon -c tetragon -- tetra getevents -o compact
-```
+```

install/kubernetes/tetragon/templates/tetragon_configmap.yaml

@@ -25,6 +25,8 @@ data:
 {{- .Values.tetragon.exportDenyList | trim | nindent 4 }}
   field-filters: |-
 {{- .Values.tetragon.fieldFilters | trim | nindent 4 }}
+  redaction-filters: |-
+{{- .Values.tetragon.redactionFilters | trim | nindent 4 }}
   export-rate-limit: {{ .Values.tetragon.exportRateLimit | quote }}
 {{- end }}
 {{- if .Values.tetragon.enableK8sAPI }}

install/kubernetes/tetragon/values.yaml

@@ -111,7 +111,37 @@ tetragon:
   #   {"event_set": ["PROCESS_KPROBE"], "fields": "process", "action": "INCLUDE"}
   #
   fieldFilters: |-
-    {}
+
+  # Filters to redact secrets from string fields in Tetragon events.  To perform
+  # redactions, redaction filters define regular expressions in the `redact`
+  # field. Any capture groups in these regular expressions are redacted and
+  # replaced with "*****".
+  #
+  # Redaction filters select events using the `match` field, which contains one
+  # or more filters (these filters are defined the same way as export filters).
+  # If no match filter is defined, all events are selected.
+  #
+  # NOTE: When writing regular expressions in JSON, it is important to escape
+  # backslash characters. For instance `\Wpasswd\W?` would be written as
+  # `{"redact": "\\Wpasswd\\W?"}`.
+  #
+  # As a concrete example, the following will redact all passwords passed to
+  # processes with the "--password" argument:
+  #
+  #   {"redact": ["--password(?:\\s+|=)(\\S*)"]}
+  #
+  # Now, an event which contains the string "--password=foo" would have that
+  # string replaced with "--password=*****".
+  #
+  # Suppose we also see some passwords passed via the -p shorthand for a specific binary, foo.
+  # We can also redact these as follows:
+  #
+  #   {"match": [{"binary_regex": "(?:^|/)foo$"}], "redact": ["-p(?:\\s+|=)(\\S*)"]}
+  #
+  # With both of the above redaction filters in place, we are now redacting all
+  # password arguments.
+  redactionFilters: |-
+
   # Access Kubernetes API to associate Tetragon events with Kubernetes pods.
   enableK8sAPI: true
   # enableProcessCred enables Capabilities visibility in exec and kprobe events.
@@ -171,7 +201,7 @@ tetragon:
     installDir: "/opt/tetragon"
     # -- Security context for oci-hook-setup init container
     securityContext:
-       privileged: true
+      privileged: true
     # -- Extra volume mounts to add to the oci-hook-setup init container
     extraVolumeMounts: []
     # -- resources for the the oci-hook-setup init container

pkg/bench/bench.go

@@ -24,6 +24,7 @@ import (
 	"github.com/cilium/tetragon/pkg/cilium"
 	"github.com/cilium/tetragon/pkg/defaults"
 	"github.com/cilium/tetragon/pkg/exporter"
+	"github.com/cilium/tetragon/pkg/fieldfilters"
 	"github.com/cilium/tetragon/pkg/grpc"
 	"github.com/cilium/tetragon/pkg/logger"
 	"github.com/cilium/tetragon/pkg/observer"
@@ -227,7 +228,8 @@ func startBenchmarkExporter(ctx context.Context, obs *observer.Observer, summary
 		ctx,
 		&wg,
 		observer.GetSensorManager(),
-		hookRunner)
+		hookRunner,
+		fieldfilters.RedactionFilterList{})
 	if err != nil {
 		return err
 	}

pkg/exporter/exporter_test.go

@@ -15,6 +15,7 @@ import (
 
 	"github.com/cilium/tetragon/api/v1/tetragon"
 	"github.com/cilium/tetragon/pkg/encoder"
+	"github.com/cilium/tetragon/pkg/fieldfilters"
 	"github.com/cilium/tetragon/pkg/ratelimit"
 	"github.com/cilium/tetragon/pkg/rthooks"
 	"github.com/cilium/tetragon/pkg/server"
@@ -85,7 +86,7 @@ func TestExporter_Send(t *testing.T) {
 	eventNotifier := newFakeNotifier()
 	ctx, cancel := context.WithCancel(context.Background())
 	dr := rthooks.DummyHookRunner{}
-	grpcServer := server.NewServer(ctx, &wg, eventNotifier, &server.FakeObserver{}, dr)
+	grpcServer := server.NewServer(ctx, &wg, eventNotifier, &server.FakeObserver{}, dr, fieldfilters.RedactionFilterList{})
 	numRecords := 2
 	results := newArrayWriter(numRecords)
 	encoder := encoder.NewProtojsonEncoder(results)
@@ -190,7 +191,7 @@ func Test_rateLimitExport(t *testing.T) {
 			ctx, cancel := context.WithCancel(context.Background())
 			eventNotifier := newFakeNotifier()
 			dr := rthooks.DummyHookRunner{}
-			grpcServer := server.NewServer(ctx, &wg, eventNotifier, &server.FakeObserver{}, dr)
+			grpcServer := server.NewServer(ctx, &wg, eventNotifier, &server.FakeObserver{}, dr, fieldfilters.RedactionFilterList{})
 			results := newArrayWriter(tt.totalEvents)
 			encoder := encoder.NewProtojsonEncoder(results)
 			request := &tetragon.GetEventsRequest{}