json.loads()容易受到任意代码执行的攻击吗?
问题描述
来自Python标准json
模块的json.loads
是否易受任意代码执行或任何其他安全问题的攻击?
我的应用程序可以接收来自不可信源的JSON消息。
解决方案
请注意,以下答案与Windows1064位的默认Python3.4安装相关。另请注意,此答案仅查看py扫描程序,而不是c扫描程序。
有关源文件,请参阅https://hg.python.org/cpython/file/tip/Lib/json或在本地python安装中找到它们。
研究
请参阅本文底部本研究旁边的参考实现
json.loads(s)
调用的解析函数在Libjsonscanner.py
中定义:
parse_object = context.parse_object
parse_array = context.parse_array
parse_string = context.parse_string
parse_float = context.parse_float
parse_int = context.parse_int
parse_constant = context.parse_constant
context
是JSONDecoder
中定义的JSONDecoder
类的实例,使用以下解析器:
self.parse_float = parse_float or float
self.parse_int = parse_int or int
self.parse_constant = parse_constant or _CONSTANTS.__getitem__
self.parse_string = scanstring
self.parse_object = JSONObject
self.parse_array = JSONArray
从这里我们可以查看每个单独的解析器,以确定它是否容易受到任意代码执行的影响:
PARSE_FLOAT 这使用默认的
float
函数,因此是安全的。
parse_int 这使用默认的
int
函数,因此是安全的。
parse_constant
_CONSTANTS
在同一个文件中定义为:
_CONSTANTS = {
'-Infinity': NegInf,
'Infinity': PosInf,
'NaN': NaN,
}
所以执行了一个简单的查找,所以它是安全的。
parse_string、JSONObject、JSONArray
通过查看本文末尾的实现可以看到,唯一可以执行的外部代码是:
发件人JSONObject
:
object_pairs_hook
object_hook
发件人JSONArray
:
scan_once
object_pairs_hook
,object_hook
默认情况下object_pairs_hook
和object_hook
定义为来自解码器初始值设定项的None
:
def __init__(self, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, strict=True,
object_pairs_hook=None)
scan_once
scan_once
定义为:
self.scan_once = scanner.make_scanner(self)
其源可以在Libjsonscanner.py
中找到,从中我们可以看到它scan_once
只是为JSON对象的每个部分调用了相应的解析器。
结论
从上面和参考实现可以看出,只要JSON解码器使用的扫描器是默认的,就不会执行任意代码,很可能通过使用自定义解码器的__init__
参数来使其执行任意代码,但是我不这么认为。
实施
反斜杠
BACKSLASH = {
'"': '"', '\': '\', '/': '/',
'b': '', 'f': 'f', 'n': '
', 'r': '', 't': ' ',
}
字符串
STRINGCHUNK = re.compile(r'(.*?)(["\x00-x1f])', FLAGS)
扫描字符串
def py_scanstring(s, end, strict=True,
_b=BACKSLASH, _m=STRINGCHUNK.match):
"""Scan the string s for a JSON string. End is the index of the
character in s after the quote that started the JSON string.
Unescapes all valid JSON string escape sequences and raises ValueError
on attempt to decode an invalid string. If strict is False then literal
control characters are allowed in the string.
Returns a tuple of the decoded string and the index of the character in s
after the end quote."""
chunks = []
_append = chunks.append
begin = end - 1
while 1:
chunk = _m(s, end)
if chunk is None:
raise ValueError(
errmsg("Unterminated string starting at", s, begin))
end = chunk.end()
content, terminator = chunk.groups()
# Content is contains zero or more unescaped string characters
if content:
_append(content)
# Terminator is the end of string, a literal control character,
# or a backslash denoting that an escape sequence follows
if terminator == '"':
break
elif terminator != '\':
if strict:
#msg = "Invalid control character %r at" % (terminator,)
msg = "Invalid control character {0!r} at".format(terminator)
raise ValueError(errmsg(msg, s, end))
else:
_append(terminator)
continue
try:
esc = s[end]
except IndexError:
raise ValueError(
errmsg("Unterminated string starting at", s, begin))
# If not a unicode escape sequence, must be in the lookup table
if esc != 'u':
try:
char = _b[esc]
except KeyError:
msg = "Invalid \escape: {0!r}".format(esc)
raise ValueError(errmsg(msg, s, end))
end += 1
else:
uni = _decode_uXXXX(s, end)
end += 5
if 0xd800 <= uni <= 0xdbff and s[end:end + 2] == '\u':
uni2 = _decode_uXXXX(s, end + 1)
if 0xdc00 <= uni2 <= 0xdfff:
uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
end += 6
char = chr(uni)
_append(char)
return ''.join(chunks), end
scanstring = c_scanstring or py_scanstring
空格
WHITESPACE = re.compile(r'[
]*', FLAGS)
WHITESPACE_STR
WHITESPACE_STR = '
'
JSONObject
def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
memo=None, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
s, end = s_and_end
pairs = []
pairs_append = pairs.append
# Backwards compatibility
if memo is None:
memo = {}
memo_get = memo.setdefault
# Use a slice to prevent IndexError from being raised, the following
# check will raise a more specific ValueError if the string is empty
nextchar = s[end:end + 1]
# Normally we expect nextchar == '"'
if nextchar != '"':
if nextchar in _ws:
end = _w(s, end).end()
nextchar = s[end:end + 1]
# Trivial empty object
if nextchar == '}':
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end + 1
pairs = {}
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end + 1
elif nextchar != '"':
raise ValueError(errmsg(
"Expecting property name enclosed in double quotes", s, end))
end += 1
while True:
key, end = scanstring(s, end, strict)
key = memo_get(key, key)
# To skip some function call overhead we optimize the fast paths where
# the JSON key separator is ": " or just ":".
if s[end:end + 1] != ':':
end = _w(s, end).end()
if s[end:end + 1] != ':':
raise ValueError(errmsg("Expecting ':' delimiter", s, end))
end += 1
try:
if s[end] in _ws:
end += 1
if s[end] in _ws:
end = _w(s, end + 1).end()
except IndexError:
pass
try:
value, end = scan_once(s, end)
except StopIteration as err:
raise ValueError(errmsg("Expecting value", s, err.value)) from None
pairs_append((key, value))
try:
nextchar = s[end]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end]
except IndexError:
nextchar = ''
end += 1
if nextchar == '}':
break
elif nextchar != ',':
raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1))
end = _w(s, end).end()
nextchar = s[end:end + 1]
end += 1
if nextchar != '"':
raise ValueError(errmsg(
"Expecting property name enclosed in double quotes", s, end - 1))
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end
pairs = dict(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end
JSONArray
def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
s, end = s_and_end
values = []
nextchar = s[end:end + 1]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
# Look-ahead for trivial empty array
if nextchar == ']':
return values, end + 1
_append = values.append
while True:
try:
value, end = scan_once(s, end)
except StopIteration as err:
raise ValueError(errmsg("Expecting value", s, err.value)) from None
_append(value)
nextchar = s[end:end + 1]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
end += 1
if nextchar == ']':
break
elif nextchar != ',':
raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1))
try:
if s[end] in _ws:
end += 1
if s[end] in _ws:
end = _w(s, end + 1).end()
except IndexError:
pass
return values, end
scanner.make_scanner
def py_make_scanner(context):
parse_object = context.parse_object
parse_array = context.parse_array
parse_string = context.parse_string
match_number = NUMBER_RE.match
strict = context.strict
parse_float = context.parse_float
parse_int = context.parse_int
parse_constant = context.parse_constant
object_hook = context.object_hook
object_pairs_hook = context.object_pairs_hook
memo = context.memo
def _scan_once(string, idx):
try:
nextchar = string[idx]
except IndexError:
raise StopIteration(idx)
if nextchar == '"':
return parse_string(string, idx + 1, strict)
elif nextchar == '{':
return parse_object((string, idx + 1), strict,
_scan_once, object_hook, object_pairs_hook, memo)
elif nextchar == '[':
return parse_array((string, idx + 1), _scan_once)
elif nextchar == 'n' and string[idx:idx + 4] == 'null':
return None, idx + 4
elif nextchar == 't' and string[idx:idx + 4] == 'true':
return True, idx + 4
elif nextchar == 'f' and string[idx:idx + 5] == 'false':
return False, idx + 5
m = match_number(string, idx)
if m is not None:
integer, frac, exp = m.groups()
if frac or exp:
res = parse_float(integer + (frac or '') + (exp or ''))
else:
res = parse_int(integer)
return res, m.end()
elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
return parse_constant('NaN'), idx + 3
elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
return parse_constant('Infinity'), idx + 8
elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
return parse_constant('-Infinity'), idx + 9
else:
raise StopIteration(idx)
def scan_once(string, idx):
try:
return _scan_once(string, idx)
finally:
memo.clear()
return _scan_once
make_scanner = c_make_scanner or py_make_scanner
相关文章