Merge remote-tracking branch 'origin/dev'

Bumping version, noting changes since last release.

Signed-off-by: Mark Stemm <mark.stemm@gmail.com>

.cmake-format

@@ -0,0 +1,119 @@
+# --------------------------
+# General Formatting Options
+# --------------------------
+# How wide to allow formatted cmake files
+line_width = 80
+
+# How many spaces to tab for indent
+tab_size = 2
+
+# If arglists are longer than this, break them always
+max_subargs_per_line = 3
+
+# If true, separate flow control names from their parentheses with a space
+separate_ctrl_name_with_space = False
+
+# If true, separate function names from parentheses with a space
+separate_fn_name_with_space = False
+
+# If a statement is wrapped to more than one line, than dangle the closing
+# parenthesis on it's own line
+dangle_parens = False
+
+# If the statement spelling length (including space and parenthesis is larger
+# than the tab width by more than this amoung, then force reject un-nested
+# layouts.
+max_prefix_chars = 2
+
+# If a candidate layout is wrapped horizontally but it exceeds this many lines,
+# then reject the layout.
+max_lines_hwrap = 2
+
+# What style line endings to use in the output.
+line_ending = 'unix'
+
+# Format command names consistently as 'lower' or 'upper' case
+command_case = 'canonical'
+
+# Format keywords consistently as 'lower' or 'upper' case
+keyword_case = 'unchanged'
+
+# Specify structure for custom cmake functions
+additional_commands = {
+  "pkg_find": {
+    "kwargs": {
+      "PKG": "*"
+    }
+  }
+}
+
+# A list of command names which should always be wrapped
+always_wrap = []
+
+# Specify the order of wrapping algorithms during successive reflow attempts
+algorithm_order = [0, 1, 2, 3, 4]
+
+# If true, the argument lists which are known to be sortable will be sorted
+# lexicographicall
+enable_sort = True
+
+# If true, the parsers may infer whether or not an argument list is sortable
+# (without annotation).
+autosort = False
+
+# If a comment line starts with at least this many consecutive hash characters,
+# then don't lstrip() them off. This allows for lazy hash rulers where the first
+# hash char is not separated by space
+hashruler_min_length = 10
+
+# A dictionary containing any per-command configuration overrides. Currently
+# only `command_case` is supported.
+per_command = {}
+
+
+# --------------------------
+# Comment Formatting Options
+# --------------------------
+# What character to use for bulleted lists
+bullet_char = '*'
+
+# What character to use as punctuation after numerals in an enumerated list
+enum_char = '.'
+
+# enable comment markup parsing and reflow
+enable_markup = True
+
+# If comment markup is enabled, don't reflow the first comment block in each
+# listfile. Use this to preserve formatting of your copyright/license
+# statements.
+first_comment_is_literal = False
+
+# If comment markup is enabled, don't reflow any comment block which matches
+# this (regex) pattern. Default is `None` (disabled).
+literal_comment_pattern = None
+
+# Regular expression to match preformat fences in comments
+# default=r'^\s*([`~]{3}[`~]*)(.*)$'
+fence_pattern = '^\\s*([`~]{3}[`~]*)(.*)$'
+
+# Regular expression to match rulers in comments
+# default=r'^\s*[^\w\s]{3}.*[^\w\s]{3}$'
+ruler_pattern = '^\\s*[^\\w\\s]{3}.*[^\\w\\s]{3}$'
+
+# If true, then insert a space between the first hash char and remaining hash
+# chars in a hash ruler, and normalize it's length to fill the column
+canonicalize_hashrulers = True
+
+
+# ---------------------------------
+# Miscellaneous Options
+# ---------------------------------
+# If true, emit the unicode byte-order mark (BOM) at the start of the file
+emit_byteorder_mark = False
+
+# Specify the encoding of the input file. Defaults to utf-8.
+input_encoding = 'utf-8'
+
+# Specify the encoding of the output file. Defaults to utf-8. Note that cmake
+# only claims to support utf-8 so be careful when using anything else
+output_encoding = 'utf-8'

.gitignore

@@ -20,4 +20,7 @@ docker/event-generator/mysqld
 docker/event-generator/httpd
 docker/event-generator/sha1sum
 docker/event-generator/vipw
-.vscode/*
+
+.vscode/*
+
+.luacheckcache

.luacheckrc

@@ -0,0 +1,9 @@
+std = "min"
+cache = true
+include_files = {
+    "userspace/falco/lua/*.lua",
+    "userspace/engine/lua/*.lua",
+    "userspace/engine/lua/lyaml/*.lua",
+    "*.luacheckrc"
+}
+exclude_files = {"build"}

.yamllint.conf

@@ -0,0 +1,8 @@
+extends: default
+
+rules:
+  indentation: disable
+  document-start: disable
+  comments: disable
+  line-length: disable
+  new-line-at-end-of-file: disable

CHANGELOG.md

@@ -2,6 +2,74 @@
 
 This file documents all notable changes to Falco. The release numbering uses [semantic versioning](http://semver.org).
 
+## v0.16.0
+
+Released 2019-07-12
+
+## Major Changes
+
+* Clean up error reporting to provide more meaningful error messages along with context when loading rules files. When run with -V, the results of the validation ("OK" or error message) are sent to standard output. [[#708](https://github.com/falcosecurity/falco/pull/708)]
+
+* Improve rule loading performance by optimizing lua parsing paths to avoid expensive pattern matches. [[#694](https://github.com/falcosecurity/falco/pull/694)]
+
+* Bump falco engine version to 4 to reflect new fields `ka.useragent`, others. [[#710](https://github.com/falcosecurity/falco/pull/710)] [[#681](https://github.com/falcosecurity/falco/pull/681)]
+
+* Add Catch2 as a unit testing framework. This will add additional coverage on top of the regression tests using Avocado. [[#687](https://github.com/falcosecurity/falco/pull/687)]
+
+## Minor Changes
+
+* Add SYSDIG_DIR Cmake option to specify location for sysdig source code when building falco. [[#677](https://github.com/falcosecurity/falco/pull/677)] [[#679](https://github.com/falcosecurity/falco/pull/679)] [[#702](https://github.com/falcosecurity/falco/pull/702)]
+
+* New field `ka.useragent` reports the useragent from k8s audit events. [[#709](https://github.com/falcosecurity/falco/pull/709)]
+
+* Add clang formatter for C++ syntax formatting. [[#701](https://github.com/falcosecurity/falco/pull/701)] [[#689](https://github.com/falcosecurity/falco/pull/689)]
+
+* Partial changes towards lua syntax formatting. No particular formatting enforced yet, though. [[#718](https://github.com/falcosecurity/falco/pull/718)]
+
+* Partial changes towards yaml syntax formatting. No particular formatting enforced yet, though. [[#714](https://github.com/falcosecurity/falco/pull/714)]
+
+* Add cmake syntax formatting. [[#703](https://github.com/falcosecurity/falco/pull/703)]
+
+* Token bucket unit tests and redesign. [[#692](https://github.com/falcosecurity/falco/pull/692)]
+
+* Update github PR template. [[#699](https://github.com/falcosecurity/falco/pull/699)]
+
+* Fix PR template for kind/rule-*. [[#697](https://github.com/falcosecurity/falco/pull/697)]
+
+## Bug Fixes
+
+* Remove an unused cmake file. [[#700](https://github.com/falcosecurity/falco/pull/700)]
+
+* Misc Cmake cleanups. [[#673](https://github.com/falcosecurity/falco/pull/673)]
+
+* Misc k8s install docs improvements. [[#671](https://github.com/falcosecurity/falco/pull/671)]
+
+## Rule Changes
+
+* Allow k8s.gcr.io/kube-proxy image to run privileged. [[#717](https://github.com/falcosecurity/falco/pull/717)]
+
+* Add runc to the list of possible container entrypoint parents. [[#712](https://github.com/falcosecurity/falco/pull/712)]
+
+* Skip Source RFC 1918 addresses when considering outbound connections. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add additional `user_XXX` placeholder macros to allow for easy customization of rule exceptions. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Let weaveworks programs change namespaces. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add additional openshift images. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add openshift as a k8s binary. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Add dzdo as a binary that can change users. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Allow azure/calico binaries to change namespaces. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Add back trusted_containers list for backport compatibility [[#675](https://github.com/falcosecurity/falco/pull/675)]
+
+* Add mkdirat as a syscall for mkdir operations. [[#667](https://github.com/falcosecurity/falco/pull/667)]
+
+* Add container id/repository to rules that can work with containers. [[#667](https://github.com/falcosecurity/falco/pull/667)]
+
 ## v0.15.3
 
 Released 2019-06-12

README.md

@@ -5,7 +5,7 @@
 
 #### Latest release
 
-**v0.15.3**
+**v0.16.0**
 Read the [change log](https://github.com/falcosecurity/falco/blob/dev/CHANGELOG.md)
 
 Dev Branch: [![Build Status](https://travis-ci.com/falcosecurity/falco.svg?branch=dev)](https://travis-ci.com/falcosecurity/falco)<br />

falco.yaml

@@ -166,4 +166,5 @@ program_output:
 
 http_output:
   enabled: false
-  url: http://some.url
+  url: http://some.url
+

integrations/k8s-using-daemonset/README.md

@@ -59,7 +59,8 @@ Now that we have the requirements for our Daemon Set in place, we can create our
 
 ```
 k8s-using-daemonset$ kubectl create -f k8s-with-rbac/falco-daemonset-configmap.yaml
-daemonset "falco" created
+daemonset.extensions "falco-daemonset" created
+
 k8s-using-daemonset$
 ```
 
@@ -97,14 +98,13 @@ In order to test that Falco is working correctly, you can launch a shell in a Po
 
 ```
 k8s-using-daemonset$ kubectl get pods
-NAME          READY     STATUS    RESTARTS   AGE
-falco-74htl   1/1       Running   0          13h
-falco-fqz2m   1/1       Running   0          13h
-falco-sgjfx   1/1       Running   0          13h
-k8s-using-daemonset$ kubectl exec -it falco-74htl bash
-root@falco-74htl:/# exit
-k8s-using-daemonset$ kubectl logs falco-74htl
-{"output":"17:48:58.590038385: Notice A shell was spawned in a container with an attached terminal (user=root k8s.pod=falco-74htl container=a98c2aa8e670 shell=bash parent=<NA> cmdline=bash  terminal=34816)","priority":"Notice","rule":"Terminal shell in container","time":"2017-12-20T17:48:58.590038385Z", "output_fields": {"container.id":"a98c2aa8e670","evt.time":1513792138590038385,"k8s.pod.name":"falco-74htl","proc.cmdline":"bash ","proc.name":"bash","proc.pname":null,"proc.tty":34816,"user.name":"root"}}
+NAME                    READY     STATUS    RESTARTS   AGE
+falco-daemonset-b695d   1/1       Running   0          2d
+falco-daemonset-n8q2v   1/1       Running   0          2d
+k8s-using-daemonset$ kubectl exec -it falco-daemonset-b695d bash
+root@falco-daemonset-b695d:/# exit
+k8s-using-daemonset$ kubectl logs falco-daemonset-b695d
+07:16:09.217866519: Error File below known binary directory renamed/removed (user=root command=event_generator pcmdline=<NA> operation=rename file=<NA> res=0 oldpath=/bin/true newpath=/bin/true.event-generator-sh ) k8s.ns=default k8s.pod=falco-event-generator-deployment-645444689b-j6mth container=0e67aad65846 k8s.ns=default k8s.pod=falco-event-generator-deployment-645444689b-j6mth container=0e67aad65846
 k8s-using-daemonset$
 ```
 

rules/falco_rules.yaml

@@ -1740,7 +1740,7 @@
     docker.io/sysdig/agent, docker.io/sysdig/falco, docker.io/sysdig/sysdig,
     gcr.io/google_containers/kube-proxy, docker.io/calico/node,
     docker.io/rook/toolbox, docker.io/cloudnativelabs/kube-router, docker.io/mesosphere/mesos-slave,
-    docker.io/docker/ucp-agent, sematext_images
+    docker.io/docker/ucp-agent, sematext_images, k8s.gcr.io/kube-proxy
     ]
 
 - macro: falco_privileged_containers
@@ -1832,7 +1832,7 @@
 # when we lose events and lose track of state.
 
 - macro: container_entrypoint
-  condition: (not proc.pname exists or proc.pname in (runc:[0:PARENT], runc:[1:CHILD], docker-runc, exe))
+  condition: (not proc.pname exists or proc.pname in (runc:[0:PARENT], runc:[1:CHILD], runc, docker-runc, exe))
 
 - rule: Launch Sensitive Mount Container
   desc: >
@@ -2253,7 +2253,7 @@
   condition: >
     spawned_process and container and
     ((proc.name = "nc" and (proc.args contains "-e" or proc.args contains "-c")) or
-     (proc.name = "ncat" and (proc.args contains "--sh-exec" or proc.args contains "--exec" or proc.args contains "-e " 
+     (proc.name = "ncat" and (proc.args contains "--sh-exec" or proc.args contains "--exec" or proc.args contains "-e "
                               or proc.args contains "-c " or proc.args contains "--lua-exec"))
     )
   output: >

test/rules/invalid_condition_not_rule.yaml

@@ -0,0 +1,5 @@
+- rule: condition not rule
+  condition:
+  desc: some desc
+  output: some output
+  priority: INFO

test/rules/invalid_macro_comple_error.yaml

@@ -0,0 +1,2 @@
+- macro: macro with comp error
+  condition: gak

userspace/engine/falco_engine_version.h

@@ -19,9 +19,9 @@ limitations under the License.
 
 // The version of rules/filter fields/etc supported by this falco
 // engine.
-#define FALCO_ENGINE_VERSION (3)
+#define FALCO_ENGINE_VERSION (4)
 
 // This is the result of running "falco --list -N | sha256sum" and
 // represents the fields supported by this version of falco. It's used
 // at build time to detect a changed set of fields.
-#define FALCO_FIELDS_CHECKSUM "9b5557ec8f16f5606a1544573b152d211d5212f653ee039146836a17266ff449"
+#define FALCO_FIELDS_CHECKSUM "ceb069d9f9b2d4ebcc5de39bddc53b7af2e6b8f072edc293668fd6ac4e532413"

userspace/engine/json_evt.cpp

@@ -19,8 +19,8 @@ limitations under the License.
 
 #include <ctype.h>
 
-#include "utils.h"
 #include "uri.h"
+#include "utils.h"
 
 #include "falco_common.h"
 #include "json_evt.h"
@@ -30,7 +30,6 @@ using namespace std;
 
 json_event::json_event()
 {
-
 }
 
 json_event::~json_event()
@@ -60,7 +59,7 @@ std::string json_event_filter_check::def_format(const json &j, std::string &fiel
 
 std::string json_event_filter_check::json_as_string(const json &j)
 {
-	if (j.type() == json::value_t::string)
+	if(j.type() == json::value_t::string)
 	{
 		return j;
 	}
@@ -70,32 +69,35 @@ std::string json_event_filter_check::json_as_string(const json &j)
 	}
 }
 
-json_event_filter_check::field_info::field_info()
-	: m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
+json_event_filter_check::field_info::field_info():
+	m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
 {
 }
 
 json_event_filter_check::field_info::field_info(std::string name,
-						std::string desc)
-	: m_name(name), m_desc(desc),
-	  m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
+						std::string desc):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
 {
 }
 
 json_event_filter_check::field_info::field_info(std::string name,
 						std::string desc,
-						index_mode mode)
-	: m_name(name), m_desc(desc),
-	  m_idx_mode(mode), m_idx_type(IDX_NUMERIC)
+						index_mode mode):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(mode), m_idx_type(IDX_NUMERIC)
 {
 }
 
 json_event_filter_check::field_info::field_info(std::string name,
 						std::string desc,
 						index_mode mode,
-						index_type itype)
-	: m_name(name), m_desc(desc),
-	  m_idx_mode(mode), m_idx_type(itype)
+						index_type itype):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(mode), m_idx_type(itype)
 {
 }
 
@@ -107,14 +109,15 @@ json_event_filter_check::alias::alias()
 {
 }
 
-json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr)
-	: m_jptr(ptr), m_format(def_format)
+json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr):
+	m_jptr(ptr), m_format(def_format)
 {
 }
 
 json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr,
-				      format_t format)
-	: m_jptr(ptr), m_format(format)
+				      format_t format):
+	m_jptr(ptr),
+	m_format(format)
 {
 }
 
@@ -122,8 +125,8 @@ json_event_filter_check::alias::~alias()
 {
 }
 
-json_event_filter_check::json_event_filter_check()
-	: m_format(def_format)
+json_event_filter_check::json_event_filter_check():
+	m_format(def_format)
 {
 }
 
@@ -150,7 +153,7 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 
 		// What follows the match must not be alphanumeric or a dot
 		if(strncmp(info.m_name.c_str(), str, info.m_name.size()) == 0 &&
-		   !isalnum((int) str[info.m_name.size()]) &&
+		   !isalnum((int)str[info.m_name.size()]) &&
 		   str[info.m_name.size()] != '.' &&
 		   info.m_name.size() > match_len)
 		{
@@ -169,7 +172,7 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 
 				if(end != NULL)
 				{
-					m_idx = string(start, end-start);
+					m_idx = string(start, end - start);
 				}
 
 				idx_len = (end - start + 2);
@@ -197,14 +200,14 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 	return match_len + idx_len;
 }
 
-void json_event_filter_check::add_filter_value(const char* str, uint32_t len, uint32_t i)
+void json_event_filter_check::add_filter_value(const char *str, uint32_t len, uint32_t i)
 {
 	m_values.push_back(string(str));
 }
 
 bool json_event_filter_check::compare(gen_event *evt)
 {
-	json_event *jevt = (json_event *) evt;
+	json_event *jevt = (json_event *)evt;
 
 	std::string value = extract(jevt);
 
@@ -225,7 +228,7 @@ bool json_event_filter_check::compare(gen_event *evt)
 	case CO_IN:
 		for(auto &val : m_values)
 		{
-			if (value == val)
+			if(value == val)
 			{
 				return true;
 			}
@@ -268,11 +271,12 @@ json_event_filter_check::check_info &json_event_filter_check::get_fields()
 	return m_info;
 }
 
-uint8_t* json_event_filter_check::extract(gen_event *evt, uint32_t* len, bool sanitize_strings)
+uint8_t *json_event_filter_check::extract(gen_event *evt, uint32_t *len, bool sanitize_strings)
 {
-	json_event *jevt = (json_event *) evt;
+	json_event *jevt = (json_event *)evt;
 
-	try {
+	try
+	{
 		const json &j = jevt->jevt().at(m_jptr);
 
 		// Only format when the value was actually found in
@@ -286,7 +290,7 @@ uint8_t* json_event_filter_check::extract(gen_event *evt, uint32_t* len, bool sa
 
 	*len = m_tstr.size();
 
-	return (uint8_t *) m_tstr.c_str();
+	return (uint8_t *)m_tstr.c_str();
 }
 
 std::string json_event_filter_check::extract(json_event *evt)
@@ -299,7 +303,7 @@ std::string json_event_filter_check::extract(json_event *evt)
 
 	if(res != NULL)
 	{
-		ret.assign((const char *) res, len);
+		ret.assign((const char *)res, len);
 	}
 
 	return ret;
@@ -315,18 +319,15 @@ jevt_filter_check::jevt_filter_check()
 {
 	m_info = {"jevt",
 		  "generic ways to access json events",
-		  {
-			  {s_jevt_time_field, "json event timestamp as a string that includes the nanosecond part"},
-			  {s_jevt_time_iso_8601_field, "json event timestamp in ISO 8601 format, including nanoseconds and time zone offset (in UTC)"},
-			  {s_jevt_rawtime_field, "absolute event timestamp, i.e. nanoseconds from epoch."},
-			  {s_jevt_value_field, "General way to access single property from json object. The syntax is [<json pointer expression>]. The property is returned as a string", IDX_REQUIRED, IDX_KEY},
-			  {s_jevt_obj_field, "The entire json object, stringified"}
-		  }};
+		  {{s_jevt_time_field, "json event timestamp as a string that includes the nanosecond part"},
+		   {s_jevt_time_iso_8601_field, "json event timestamp in ISO 8601 format, including nanoseconds and time zone offset (in UTC)"},
+		   {s_jevt_rawtime_field, "absolute event timestamp, i.e. nanoseconds from epoch."},
+		   {s_jevt_value_field, "General way to access single property from json object. The syntax is [<json pointer expression>]. The property is returned as a string", IDX_REQUIRED, IDX_KEY},
+		   {s_jevt_obj_field, "The entire json object, stringified"}}};
 }
 
 jevt_filter_check::~jevt_filter_check()
 {
-
 }
 
 int32_t jevt_filter_check::parse_field_name(const char *str, bool alloc_state, bool needed_for_filtering)
@@ -360,55 +361,56 @@ int32_t jevt_filter_check::parse_field_name(const char *str, bool alloc_state, b
 		const char *end;
 
 		// What follows must be [<json pointer expression>]
-		if (*(str + s_jevt_value_field.size()) != '[' ||
-		    ((end = strchr(str + 1, ']')) == NULL))
+		if(*(str + s_jevt_value_field.size()) != '[' ||
+		   ((end = strchr(str + 1, ']')) == NULL))
 
 		{
 			throw falco_exception(string("Could not parse filtercheck field \"") + str + "\". Did not have expected format with 'jevt.value[<json pointer>]'");
 		}
 
-		try {
-			m_jptr = json::json_pointer(string(str + (s_jevt_value_field.size()+1), (end-str-(s_jevt_value_field.size()+1))));
+		try
+		{
+			m_jptr = json::json_pointer(string(str + (s_jevt_value_field.size() + 1), (end - str - (s_jevt_value_field.size() + 1))));
 		}
-		catch (json::parse_error& e)
+		catch(json::parse_error &e)
 		{
 			throw falco_exception(string("Could not parse filtercheck field \"") + str + "\". Invalid json selector (" + e.what() + ")");
 		}
 
 		// The +1 accounts for the closing ']'
-		m_field = string(str, end-str + 1);
+		m_field = string(str, end - str + 1);
 		return (end - str + 1);
 	}
 
 	return 0;
 }
 
-uint8_t* jevt_filter_check::extract(gen_event *evt, uint32_t* len, bool sanitize_stings)
+uint8_t *jevt_filter_check::extract(gen_event *evt, uint32_t *len, bool sanitize_stings)
 {
 	if(m_field == s_jevt_rawtime_field)
 	{
 		m_tstr = to_string(evt->get_ts());
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_time_field)
 	{
 		sinsp_utils::ts_to_string(evt->get_ts(), &m_tstr, false, true);
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_time_iso_8601_field)
 	{
 		sinsp_utils::ts_to_iso_8601(evt->get_ts(), &m_tstr);
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_obj_field)
 	{
-		json_event *jevt = (json_event *) evt;
+		json_event *jevt = (json_event *)evt;
 		m_tstr = jevt->jevt().dump();
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 
 	return json_event_filter_check::extract(evt, len, sanitize_stings);
@@ -418,7 +420,7 @@ json_event_filter_check *jevt_filter_check::allocate_new()
 {
 	jevt_filter_check *chk = new jevt_filter_check();
 
-	return (json_event_filter_check *) chk;
+	return (json_event_filter_check *)chk;
 }
 
 std::string k8s_audit_filter_check::index_image(const json &j, std::string &field, std::string &idx)
@@ -427,8 +429,9 @@ std::string k8s_audit_filter_check::index_image(const json &j, std::string &fiel
 
 	string image;
 
-	try {
-		image  = j[idx_num].at("image");
+	try
+	{
+		image = j[idx_num].at("image");
 	}
 	catch(json::out_of_range &e)
 	{
@@ -470,7 +473,6 @@ std::string k8s_audit_filter_check::index_has_name(const json &j, std::string &f
 	return string("false");
 }
 
-
 std::string k8s_audit_filter_check::index_query_param(const json &j, std::string &field, std::string &idx)
 {
 	string uri = j;
@@ -489,7 +491,7 @@ std::string k8s_audit_filter_check::index_query_param(const json &j, std::string
 	{
 		std::vector<std::string> param_parts = sinsp_split(part, '=');
 
-		if(param_parts.size() == 2 && uri::decode(param_parts[0], true)==idx)
+		if(param_parts.size() == 2 && uri::decode(param_parts[0], true) == idx)
 		{
 			return uri::decode(param_parts[1]);
 		}
@@ -498,7 +500,6 @@ std::string k8s_audit_filter_check::index_query_param(const json &j, std::string
 	return string("<NA>");
 }
 
-
 std::string k8s_audit_filter_check::index_generic(const json &j, std::string &field, std::string &idx)
 {
 	json item;
@@ -511,7 +512,8 @@ std::string k8s_audit_filter_check::index_generic(const json &j, std::string &fi
 	{
 		uint64_t idx_num = (idx.empty() ? 0 : stoi(idx));
 
-		try {
+		try
+		{
 			item = j[idx_num];
 		}
 		catch(json::out_of_range &e)
@@ -529,7 +531,7 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 
 	// Use the suffix of the field to determine which property to
 	// select from each object.
-	std::string prop = field.substr(field.find_last_of(".")+1);
+	std::string prop = field.substr(field.find_last_of(".") + 1);
 
 	std::string ret;
 
@@ -542,7 +544,8 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 				ret += " ";
 			}
 
-			try {
+			try
+			{
 				ret += json_event_filter_check::json_as_string(obj.at(prop));
 			}
 			catch(json::out_of_range &e)
@@ -553,7 +556,8 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 	}
 	else
 	{
-		try {
+		try
+		{
 			ret = j[stoi(idx)].at(prop);
 		}
 		catch(json::out_of_range &e)
@@ -573,7 +577,8 @@ std::string k8s_audit_filter_check::index_privileged(const json &j, std::string
 
 	if(!idx.empty())
 	{
-		try {
+		try
+		{
 			privileged = j[stoi(idx)].at(jpriv);
 		}
 		catch(json::out_of_range &e)
@@ -584,7 +589,8 @@ std::string k8s_audit_filter_check::index_privileged(const json &j, std::string
 	{
 		for(auto &container : j)
 		{
-			try {
+			try
+			{
 				if(container.at(jpriv))
 				{
 					privileged = true;
@@ -621,42 +627,41 @@ k8s_audit_filter_check::k8s_audit_filter_check()
 {
 	m_info = {"ka",
 		  "Access K8s Audit Log Events",
-		  {
-			  {"ka.auditid", "The unique id of the audit event"},
-			  {"ka.stage", "Stage of the request (e.g. RequestReceived, ResponseComplete, etc.)"},
-			  {"ka.auth.decision", "The authorization decision"},
-			  {"ka.auth.reason", "The authorization reason"},
-			  {"ka.user.name", "The user name performing the request"},
-			  {"ka.user.groups", "The groups to which the user belongs"},
-			  {"ka.impuser.name", "The impersonated user name"},
-			  {"ka.verb", "The action being performed"},
-			  {"ka.uri", "The request URI as sent from client to server"},
-			  {"ka.uri.param", "The value of a given query parameter in the uri (e.g. when uri=/foo?key=val, ka.uri.param[key] is val).", IDX_REQUIRED, IDX_KEY},
-			  {"ka.target.name", "The target object name"},
-			  {"ka.target.namespace", "The target object namespace"},
-			  {"ka.target.resource", "The target object resource"},
-			  {"ka.target.subresource", "The target object subresource"},
-			  {"ka.req.binding.subjects", "When the request object refers to a cluster role binding, the subject (e.g. account/users) being linked by the binding"},
-			  {"ka.req.binding.subject.has_name", "When the request object refers to a cluster role binding, return true if a subject with the provided name exists", IDX_REQUIRED, IDX_KEY},
-			  {"ka.req.binding.role", "When the request object refers to a cluster role binding, the role being linked by the binding"},
-			  {"ka.req.configmap.name", "If the request object refers to a configmap, the configmap name"},
-			  {"ka.req.configmap.obj", "If the request object refers to a configmap, the entire configmap object"},
-			  {"ka.req.container.image", "When the request object refers to a container, the container's images. Can be indexed (e.g. ka.req.container.image[0]). Without any index, returns the first image", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.container.image.repository", "The same as req.container.image, but only the repository part (e.g. sysdig/falco)", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.container.host_network", "When the request object refers to a container, the value of the hostNetwork flag."},
-			  {"ka.req.container.privileged", "When the request object refers to a container, whether or not any container is run privileged. With an index, return whether or not the ith container is run privileged.", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.role.rules", "When the request object refers to a role/cluster role, the rules associated with the role"},
-			  {"ka.req.role.rules.apiGroups", "When the request object refers to a role/cluster role, the api groups associated with the role's rules. With an index, return only the api groups from the ith rule. Without an index, return all api groups concatenated", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.role.rules.nonResourceURLs", "When the request object refers to a role/cluster role, the non resource urls associated with the role's rules. With an index, return only the non resource urls from the ith rule. Without an index, return all non resource urls concatenated", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.role.rules.verbs", "When the request object refers to a role/cluster role, the verbs associated with the role's rules. With an index, return only the verbs from the ith rule. Without an index, return all verbs concatenated", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.role.rules.resources", "When the request object refers to a role/cluster role, the resources associated with the role's rules. With an index, return only the resources from the ith rule. Without an index, return all resources concatenated", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.service.type", "When the request object refers to a service, the service type"},
-			  {"ka.req.service.ports", "When the request object refers to a service, the service's ports. Can be indexed (e.g. ka.req.service.ports[0]). Without any index, returns all ports", IDX_ALLOWED, IDX_NUMERIC},
-			  {"ka.req.volume.hostpath", "If the request object contains volume definitions, whether or not a hostPath volume exists that mounts the specified path from the host (...hostpath[/etc]=true if a volume mounts /etc from the host). The index can be a glob, in which case all volumes are considered to find any path matching the specified glob (...hostpath[/usr/*] would match either /usr/local or /usr/bin)", IDX_REQUIRED, IDX_KEY},
-			  {"ka.resp.name", "The response object name"},
-			  {"ka.response.code", "The response code"},
-			  {"ka.response.reason", "The response reason (usually present only for failures)"}
-		  }};
+		  {{"ka.auditid", "The unique id of the audit event"},
+		   {"ka.stage", "Stage of the request (e.g. RequestReceived, ResponseComplete, etc.)"},
+		   {"ka.auth.decision", "The authorization decision"},
+		   {"ka.auth.reason", "The authorization reason"},
+		   {"ka.user.name", "The user name performing the request"},
+		   {"ka.user.groups", "The groups to which the user belongs"},
+		   {"ka.impuser.name", "The impersonated user name"},
+		   {"ka.verb", "The action being performed"},
+		   {"ka.uri", "The request URI as sent from client to server"},
+		   {"ka.uri.param", "The value of a given query parameter in the uri (e.g. when uri=/foo?key=val, ka.uri.param[key] is val).", IDX_REQUIRED, IDX_KEY},
+		   {"ka.target.name", "The target object name"},
+		   {"ka.target.namespace", "The target object namespace"},
+		   {"ka.target.resource", "The target object resource"},
+		   {"ka.target.subresource", "The target object subresource"},
+		   {"ka.req.binding.subjects", "When the request object refers to a cluster role binding, the subject (e.g. account/users) being linked by the binding"},
+		   {"ka.req.binding.subject.has_name", "When the request object refers to a cluster role binding, return true if a subject with the provided name exists", IDX_REQUIRED, IDX_KEY},
+		   {"ka.req.binding.role", "When the request object refers to a cluster role binding, the role being linked by the binding"},
+		   {"ka.req.configmap.name", "If the request object refers to a configmap, the configmap name"},
+		   {"ka.req.configmap.obj", "If the request object refers to a configmap, the entire configmap object"},
+		   {"ka.req.container.image", "When the request object refers to a container, the container's images. Can be indexed (e.g. ka.req.container.image[0]). Without any index, returns the first image", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.container.image.repository", "The same as req.container.image, but only the repository part (e.g. sysdig/falco)", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.container.host_network", "When the request object refers to a container, the value of the hostNetwork flag."},
+		   {"ka.req.container.privileged", "When the request object refers to a container, whether or not any container is run privileged. With an index, return whether or not the ith container is run privileged.", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules", "When the request object refers to a role/cluster role, the rules associated with the role"},
+		   {"ka.req.role.rules.apiGroups", "When the request object refers to a role/cluster role, the api groups associated with the role's rules. With an index, return only the api groups from the ith rule. Without an index, return all api groups concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.nonResourceURLs", "When the request object refers to a role/cluster role, the non resource urls associated with the role's rules. With an index, return only the non resource urls from the ith rule. Without an index, return all non resource urls concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.verbs", "When the request object refers to a role/cluster role, the verbs associated with the role's rules. With an index, return only the verbs from the ith rule. Without an index, return all verbs concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.resources", "When the request object refers to a role/cluster role, the resources associated with the role's rules. With an index, return only the resources from the ith rule. Without an index, return all resources concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.service.type", "When the request object refers to a service, the service type"},
+		   {"ka.req.service.ports", "When the request object refers to a service, the service's ports. Can be indexed (e.g. ka.req.service.ports[0]). Without any index, returns all ports", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.volume.hostpath", "If the request object contains volume definitions, whether or not a hostPath volume exists that mounts the specified path from the host (...hostpath[/etc]=true if a volume mounts /etc from the host). The index can be a glob, in which case all volumes are considered to find any path matching the specified glob (...hostpath[/usr/*] would match either /usr/local or /usr/bin)", IDX_REQUIRED, IDX_KEY},
+		   {"ka.resp.name", "The response object name"},
+		   {"ka.response.code", "The response code"},
+		   {"ka.response.reason", "The response reason (usually present only for failures)"},
+		   {"ka.useragent", "The useragent of the client who made the request to the apiserver"}}};
 
 	{
 		m_aliases = {
@@ -693,21 +698,20 @@ k8s_audit_filter_check::k8s_audit_filter_check()
 			{"ka.req.volume.hostpath", {"/requestObject/spec/volumes"_json_pointer, check_hostpath_vols}},
 			{"ka.resp.name", {"/responseObject/metadata/name"_json_pointer}},
 			{"ka.response.code", {"/responseStatus/code"_json_pointer}},
-			{"ka.response.reason", {"/responseStatus/reason"_json_pointer}}
-		};
+			{"ka.response.reason", {"/responseStatus/reason"_json_pointer}},
+			{"ka.useragent", {"/userAgent"_json_pointer}}};
 	}
 }
 
 k8s_audit_filter_check::~k8s_audit_filter_check()
 {
-
 }
 
 json_event_filter_check *k8s_audit_filter_check::allocate_new()
 {
 	k8s_audit_filter_check *chk = new k8s_audit_filter_check();
 
-	return (json_event_filter_check *) chk;
+	return (json_event_filter_check *)chk;
 }
 
 json_event_filter::json_event_filter()
@@ -762,9 +766,9 @@ std::list<json_event_filter_check::check_info> &json_event_filter_factory::get_f
 	return m_info;
 }
 
-json_event_formatter::json_event_formatter(json_event_filter_factory &json_factory, std::string &format)
-	: m_format(format),
-	  m_json_factory(json_factory)
+json_event_formatter::json_event_formatter(json_event_filter_factory &json_factory, std::string &format):
+	m_format(format),
+	m_json_factory(json_factory)
 {
 	parse_format();
 }
@@ -777,7 +781,7 @@ std::string json_event_formatter::tostring(json_event *ev)
 {
 	std::string ret;
 
-	std::list<std::pair<std::string,std::string>> resolved;
+	std::list<std::pair<std::string, std::string>> resolved;
 
 	resolve_tokens(ev, resolved);
 
@@ -793,7 +797,7 @@ std::string json_event_formatter::tojson(json_event *ev)
 {
 	nlohmann::json ret;
 
-	std::list<std::pair<std::string,std::string>> resolved;
+	std::list<std::pair<std::string, std::string>> resolved;
 
 	resolve_tokens(ev, resolved);
 
@@ -828,11 +832,11 @@ void json_event_formatter::parse_format()
 		{
 			// Skip the %
 			tformat.erase(0, 1);
-			json_event_filter_check *chk = (json_event_filter_check *) m_json_factory.new_filtercheck(tformat.c_str());
+			json_event_filter_check *chk = (json_event_filter_check *)m_json_factory.new_filtercheck(tformat.c_str());
 
 			if(!chk)
 			{
-				throw falco_exception(string ("Could not parse format string \"") + m_format + "\": unknown filtercheck field " + tformat);
+				throw falco_exception(string("Could not parse format string \"") + m_format + "\": unknown filtercheck field " + tformat);
 			}
 
 			size = chk->parsed_size();
@@ -852,7 +856,7 @@ void json_event_formatter::parse_format()
 			// Empty fields are only allowed at the beginning of the string
 			if(m_tokens.size() > 0)
 			{
-				throw falco_exception(string ("Could not parse format string \"" + m_format + "\": empty filtercheck field"));
+				throw falco_exception(string("Could not parse format string \"" + m_format + "\": empty filtercheck field"));
 			}
 			continue;
 		}
@@ -864,7 +868,7 @@ void json_event_formatter::parse_format()
 	}
 }
 
-void json_event_formatter::resolve_tokens(json_event *ev, std::list<std::pair<std::string,std::string>> &resolved)
+void json_event_formatter::resolve_tokens(json_event *ev, std::list<std::pair<std::string, std::string>> &resolved)
 {
 	for(auto tok : m_tokens)
 	{

userspace/engine/rules.cpp

@@ -17,8 +17,6 @@ limitations under the License.
 
 */
 
-#include <sstream>
-
 #include "rules.h"
 #include "logger.h"
 

userspace/engine/rules.h

@@ -21,7 +21,6 @@ limitations under the License.
 
 #include <set>
 #include <memory>
-#include <regex>
 
 #include "sinsp.h"
 #include "filter.h"
@@ -58,13 +57,13 @@ class falco_rules
 	void add_filter(string &rule, std::set<uint32_t> &evttypes, std::set<uint32_t> &syscalls, std::set<string> &tags);
 	void add_k8s_audit_filter(string &rule, std::set<string> &tags);
 	void enable_rule(string &rule, bool enabled);
-	std::string get_context(const std::string &content, uint64_t line, uint64_t column);
 
 	lua_parser* m_sinsp_lua_parser;
 	lua_parser* m_json_lua_parser;
 	sinsp* m_inspector;
 	falco_engine *m_engine;
 	lua_State* m_ls;
+
 	string m_lua_load_rules = "load_rules";
 	string m_lua_ignored_syscalls = "ignored_syscalls";
 	string m_lua_ignored_events = "ignored_events";