Dotfiles/bin/.bin/webtest/analyse-headers

#!/usr/bin/env bash

set -o pipefail

die(){
	echo "$@" >&2
	exit 1
}

#RED='\033[0;31m'
RED='\033[1;31m'
YELLOW='\033[1;33m'
GREEN='\033[1;32m'
LBLUE='\033[1;34m'
LCYAN='\033[1;36m'
ORANGE='\033[0;33m'
LGREY='\033[0;37m'
BOLDJ='\033[1;37m'
NC='\033[0m' # No Color

stripAnsi(){
	sed -r "s/\x1B\[([0-9]{1,3}(;[0-9]{1,2})?)?[mGK]//g"
}

trimWhitespace(){
	sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//'
}

#wrapped echo
wecho(){
	builtin echo -e "$@" | fold -s -w 80
}

drawInBox(){
	innerWidth="45"
	echo -en "${LBLUE}╭"
	head -c $innerWidth /dev/zero | tr '\0' '-'
	echo -e "╮${NC}"
	while IFS= read -r line; do
		# The ansi characters mess up the string length so we need to strip them to calculate the width
		stripped="$(echo -n "$line" | stripAnsi)"
		leftPad=$(( ( innerWidth - ${#stripped} ) / 2))
		rightPad=$(( ( innerWidth - leftPad ) - ${#stripped} ))
		echo -en "${LBLUE}|${NC}"
		head -c $leftPad /dev/zero | tr '\0' ' '
		echo -n "$line"
		head -c $rightPad /dev/zero | tr '\0' ' '
		echo -e "${LBLUE}|${NC}"
	done
	echo -en "${LBLUE}╰"
	head -c $innerWidth /dev/zero | tr '\0' '-'
	echo -e "╯${NC}"
}

# gets the colour that should be output
# 0 = green
# 1 = yellow
# 2 = red
getColour(){
	case "$1" in
		0) echo -en "$GREEN" ;;
		1) echo -en "$YELLOW" ;;
		2) echo -en "$RED" ;;
	esac
}

printKey(){
	echo -e "Not checked\
\t${GREEN}Fine${NC}\
\t${YELLOW}Mis-configured${NC}\
\t${RED}Missing${NC}"
}

generic_version_disclosure(){
	local value
	local header
	value="$(echo "$1" | cut -d ':' -f 2- | trimWhitespace)"
	header="$(echo "$1" | cut -d ':' -f 1 | trimWhitespace)"
	echo "$header" | drawInBox
	wecho -e "The server responds with ${ORANGE}$value${NC} in the \
$header header"
	wecho -e "This is potentially un-necesary information disclosure\n\n"
	[ -n "$value" ] && return 1 || return 0
}

test_server(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2 | trimWhitespace)"
	echo "Server" | drawInBox
	wecho -e "The server responds with ${ORANGE}$value${NC} in the Server header"
	wecho -e "This is potentially un-necesary information disclosure\n\n"
	[ -n "$value" ] && return 1 || return 0
}

test_x-powered-by(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2 | trimWhitespace)"
	echo "X-Powered-By" | drawInBox
	wecho -e "The server responds with ${ORANGE}$value${NC} in the X-Powered-By header"
	wecho -e "This is potentially un-necesary information disclosure\n\n"
	[ -n "$value" ] && return 1 || return 0
}

test_x-xss-protection(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2 | grep -oE '[0-9]+' )"
	if [ "$value" = "1" ]; then
		return 0
	else
		echo "X-XSS-Protection" | drawInBox
		wecho -e "The X-XSS-Protection header asks browsers to try and prevent \
reflected cross site scripting attacks. It has been replaced in modern browsers \
by the content-security-policy although should still be included for the sake \
of old browsers\n\n"
		return 1
	fi
}

test_x-frame-options(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2 | trimWhitespace)"
	case "$value" in
		"SAMEORIGIN"|"DENY") return 0 ;;
		"ALLOW-FROM"*)
			echo "X-Frame-Opitons" | drawInBox
			wecho -e "The ALLOW-FROM derivative is obsolete and no longer works \
in modern browsers.\n\n"
			wecho -e "The Content-Security-Policy HTTP header has a \
frame-ancestors directive which you can use instead.\n\n"
			return 1
			;;
		*)
			echo "X-Frame-Opitons" | drawInBox
			wecho "The X-Frame-Options HTTP response header can be used to \
indicate whether or not a browser should be allowed to render a page in a \
<frame>, <iframe>, <embed> or <object>. Sites can use this to avoid \
click-jacking attacks, by ensuring that their content is not embedded into \
other sites."

			if echo "$headers" |
				grep -Eqi '^content-security-policy:.*frame-ancestors.*'; then
				wecho "It looks like the content security policy contains the \
frame ancestors directive. This also mitigates against the clickjacking \
although browser support isn't as strong meaning you should still include the \
x-frame-options header"
			fi

			source="
<!DOCTYPE html>
<html>
<head>
<meta charset='UTF-8' />
<meta name='viewport' content='width=device-width' />
<title>Clickjacking example</title>
<style type='text/css' media='screen'>
body{
	width: 100vw;
	height: 100vh;
	border: 2px solid black;
}
iframe{
	border: 3px solid black;
	width: 80%;
	height: 80%;
	margin: 20px auto;
	display: block;
}
h1, p{
text-align: center;
}
</style>
</head>
<body>
<h1>Clickjacking example</h1>
<iframe src='$url'>
</iframe>
<p>If content is rendered above, the site is vulnerable to clickjacking</p>
</body>
</html>
"
			wecho "To verify, type paste the following into your browser:"
			echo -e "\ndata:text/html;base64,$(echo "$source" | base64 -w 0)\n\n"

			return 2
	esac
}

#test_x-content-type-options(){
#}

test_content-security-policy(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2 | trimWhitespace)"
	# TODO: work on content security testing
	
	if [ -z "$value" ]; then
		echo "Content-Security-Policy" | drawInBox
		wecho -e "The HTTP Content-Security-Policy response header allows web site \
administrators to control resources the user agent is allowed to load for a \
given page. With a few exceptions, policies mostly involve specifying server \
origins and script endpoints. This helps guard against cross-site scripting \
attacks (XSS).\n\n"
		return 2
	elif echo "$value" | grep -q 'unsafe-inline'; then
		echo "Content-Security-Policy" | drawInBox
		wecho -e "The content security policy includes the \
${ORANGE}unsafe-inline${NC} property which allows for inline JS/CSS assets. \
This prevents the content security policy from effectively mitigating against
reflected or stored XSS attacks\n\n"
	elif echo "$value" | grep -q 'unsafe-eval'; then
		echo "Content-Security-Policy" | drawInBox
		wecho -e "The content security policy includes the \
${ORANGE}unsafe-eval${NC} property which allows for eval to be used in JS. \
This prevents the content security policy from effectively mitigating against
DOM based XSS attacks\n\n"
	fi
	return 0
}

test_strict-transport-security(){
	local value
	local ret
	local output
	local maxAge
	value="$(echo "$1" | cut -d ':' -f 2 | trimWhitespace)"
	ret=0
	output=""
	maxAge="$(echo "$value" | grep -oE 'max-age=[0-9]+' |
		grep -oE '[0-9]+')"

	if [ "$maxAge" -lt "31536000" ]; then
		output+="The max-age is set to a low value of ${ORANGE}$maxAge${NC}.
We suggest setting it to at least 31536000.\n\n"
		ret=$((ret>1 ? ret : 1))
	fi

	if ! echo "$value" | grep -q 'includeSubDomains'; then
		output+="The ${ORANGE}includeSubdomains${NC} property was not found. \
When included browsers won't connect to subdomains unless over an encrypted \
channel.\n\n"
		ret=$((ret>1 ? ret : 1))
	fi

	#if ! echo "$value" | grep -q 'preload'; then
	#	output+="The preload property "
	#	ret=$((ret>1 ? ret : 1))
	#fi

	if [ "$ret" -gt 0 ]; then
		echo "Strict-Transport-Security" | drawInBox
		wecho -e "$output"
	fi
	return $ret
}

test_set-cookie(){
	local value
	local cookieName
	local ret
	local output
	value="$(echo "$1" | cut -d ':' -f 2- | trimWhitespace)"
	cookieName="$(echo "$value" | cut -d '=' -f 1)"
	ret=0
	output=""

	if ! echo "$value" | grep -q "HttpOnly"; then
		echo "$value"
		echo "$value" | grep -qi "HttpOnly" --color always
		output+="The HttpOnly flag isn't set which means the cookie value can \
be read by JavaScript. If a malicious actor manages to run JavaScript through \
methods like XSS, they may be able to steal the contents of cookies\n\n"
		ret=$((ret>1 ? ret : 1))
	fi

	if ! echo "$value" | grep -qi "Secure"; then
		output+="The Secure flag isn't set which means the cookie could be \
sent over unencrypted channels\n\n"
		ret=$((ret>1 ? ret : 1))
	fi

	if ! echo "$value" | grep -q "SameSite=Strict"; then
		output+="The SameSite flag isn't set to Strict. The SameSite flag \
controls whether a cookie is sent with cross-origin requests, \
providing some protection against cross-site request forgery attacks.
Strict means the browser sends the cookie only for same-site requests\n\n"
		ret=$((ret>1 ? ret : 1))
	fi
	
	if [ "$ret" -gt 0 ]; then
		echo "Set-Cookie: $cookieName" | drawInBox
		wecho -e "$output"
	fi

	return "$ret"
}

test_permissions-policy(){
	if [ -z "$1" ]; then
		echo "Permissions-Policy" | drawInBox
		wecho "The Permission-Policy header replaces the Feature-Policy and is \
used to allow or disallow certain browser features or apis in the interest of \
security.\n\n"
		return 2
	fi
}

test_feature-policy(){
	if [ -z "$1" ]; then
		echo "Feature-Policy" | drawInBox
		wecho "The Feature-Policy header was used to allow or disallow certian \
browser features or apis. It has been superceded by the permissions-policy
header but should still be included for legacy browsers.\n\n"
		return 2
	fi
	if ! echo "$headers" | grep -Eqi '^permissions-policy'; then
		echo "Feature-Policy" | drawInBox
		wecho "The Feature-Policy header was used to allow or disallow certian \
browser features or apis. It has been superceded by the permissions-policy
header but should still be included for legacy browsers.
It has been highlighted because the Permissions-policy header wasn't found.\n\n"
		return 2
	fi
}

test_expect-ct(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2- | trimWhitespace)"
	if [ -z "$1" ]; then
		echo "Expect-CT" | drawInBox
		wecho "When a site enables the Expect-CT header, they are requesting \
that the browser check that any certificate for that site appears in public \
CT logs.
Initially, set the header without the enforce option but with report in order \
to check for potential breakages\n\n"
		return 2
	elif ! echo "$value" | grep -q "enforce"; then
		echo "Expect-CT" | drawInBox
		wecho "The enforce directive was not found. It can be useful to omit \
this whilst testing the header, but should be added once testing has finished.
Without the enforce directive, the browser will not refuse connections that \
violate the Certificate Transparency policy.
The Expect-CT will likely become obsolete in June 2021. Since May 2018 new \
certificates are expected to support SCTs by default. Certificates before \
March 2018 were allowed to have a lifetime of 39 months, those will all be \
expired in June 2021.\n\n"
		return 1
	fi
}

test_referer-policy-ct(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2- | trimWhitespace)"
	if [ -z "$1" ]; then
		echo "Referrer-Policy" | drawInBox
		wecho "The Referrer-Policy HTTP header controls how much referrer \
information (sent via the Referer header) should be included with requests.\n\n"
		return 2
	elif ! echo "$value" | grep -q "enforce"; then
		# TODO: add checks for different referer policy opitons
		return 1
	fi
}

test_access-control-allow-origin(){
	local value
	value="$(echo "$1" | cut -d ':' -f 2- | trimWhitespace)"
	if [ "$value" = "*" ]; then
		echo "Access-Control-Allow-Origin" | drawInBox
		wecho "The Access-Control-Allow-Origin header indicates whether the \
response can be shared with requesting code from the given origin
The value was found to be * meaning any origin. This is not normally desirable.
\n"
		return 1
	elif echo "$value" | grep -q "null"; then
		echo "Access-Control-Allow-Origin" | drawInBox
		wecho "The Access-Control-Allow-Origin header indicates whether the \
response can be shared with requesting code from the given origin
The value was found to be null. the serialization of the Origin of any \
resource that uses a non-hierarchical scheme (such as data: or file: ) and \
sandboxed documents is defined to be \"null\". Many User Agents will grant \
such documents access to a response with an Access-Control-Allow-Origin: \
\"null\" header, and any origin can create a hostile document with a \"null\" \
Origin. The \"null\" value for the ACAO header should therefore be avoided.\n\n"
		return 1
	
	fi
	return 0
}


usage(){
	echo -n "analyse-headers [OPTIONS]... URL

	Analyse the headers of a website

	Options:
	-h, --help              Display this help and exit
"
}


# Iterate over options breaking -ab into -a -b when needed and --foo=bar into
# --foo bar
optstring=h
unset options
while (($#)); do
	case $1 in
		# If option is of type -ab
		-[!-]?*)
		# Loop over each character starting with the second
		for ((i=1; i < ${#1}; i++)); do
			c=${1:i:1}

			# Add current char to options
			options+=("-$c")

			# If option takes a required argument, and it's not the last char make
			# the rest of the string its argument
			if [[ $optstring = *"$c:"* && ${1:i+1} ]]; then
				options+=("${1:i+1}")
				break
			fi
		done
		;;

		# If option is of type --foo=bar
		--?*=*) options+=("${1%%=*}" "${1#*=}") ;;
		# add --endopts for --
		--) options+=(--endopts) ;;
		# Otherwise, nothing special
		*) options+=("$1") ;;
	esac
	shift
done
set -- "${options[@]}"
unset options


# Read the options and set stuff
while [[ $1 = -?* ]]; do
	case $1 in
		-h|--help) usage; exit;;
		--) shift; break ;;
		*) die "invalid option: '$1'." ;;
	esac
	shift
done

# Store the remaining part as arguments.
args+=("$@")

url="${args[0]}"
[ -z "$url" ] && die "You need to specify a url"

# If url is -, read headers from stdin
if [ "$url" = "-" ]; then
	headers="$(cat -)"
else
	headers="$(curl -s -I "$url")"
fi

missingHeaders="x-frame-options
content-security-policy
x-xss-protection
x-content-type-options
feature-policy
permissions-policy
expect-ct"

tmpfile="$(mktemp)"
touch "$tmpfile"

printKey

echo ""

echo "$headers" | sed -n '1p'

while read -r line; do
	headerKey="$(echo "$line" | cut -d ':' -f1)"
	lowercase="$(echo "$headerKey" | tr '[:upper:]' '[:lower:]')"
	missingHeaders="$(echo -n "$missingHeaders" | sed '/'"$lowercase"'/d')"
	functionName="test_$lowercase"
	if declare -f "$functionName" > /dev/null; then
		"$functionName" "$line" >> "$tmpfile"
		colour="$(getColour "$?")"
		echo -e "${colour}$line${NC}"
	elif echo "$lowercase" | grep "version" > /dev/null; then
		# if the word version is in the line, assume version disclosure
		generic_version_disclosure "$line" >> "$tmpfile"
		colour="$(getColour "$?")"
		echo -e "${colour}$line${NC}"
	else
		echo "$line"
	fi
done<<<"$(echo "$headers" | sed '1d')" # We don't want the initial http banner

echo "$missingHeaders" | while read -r line; do
	echo -e "${RED}$line${NC}"
	functionName="test_$line"
	"$functionName" >> "$tmpfile"
done

echo ""

cat "$tmpfile"
rm "$tmpfile"