diff options
Diffstat (limited to 'examples/python_mutators')
| -rw-r--r-- | examples/python_mutators/README | 18 | ||||
| -rw-r--r-- | examples/python_mutators/XmlMutatorMin.py | 331 | ||||
| -rw-r--r-- | examples/python_mutators/common.py | 37 | ||||
| -rw-r--r-- | examples/python_mutators/example.py | 103 | ||||
| -rw-r--r-- | examples/python_mutators/simple-chunk-replace.py | 59 | ||||
| -rw-r--r-- | examples/python_mutators/wrapper_afl_min.py | 117 |
6 files changed, 665 insertions, 0 deletions
diff --git a/examples/python_mutators/README b/examples/python_mutators/README new file mode 100644 index 00000000..4e7d62bc --- /dev/null +++ b/examples/python_mutators/README @@ -0,0 +1,18 @@ +These are example and helper files for the AFL_PYTHON_MODULE feature. +See docs/python_mutators.txt for more information + +Note that if you compile with python3.7 you must use python3 scripts, and if +you use pyton2.7 to compile python2 scripts! + + +example.py - this is the template you can use, the functions are there + but they are empty + +simple-chunk-replace.py - this is a simple example where chunks are replaced + +common.py - this can be used for common functions and helpers. + the examples do not use this though. But you can :) + +wrapper_afl_min.py - mutation of XML documents, loads XmlMutatorMin.py + +XmlMutatorMin.py - module for XML mutation diff --git a/examples/python_mutators/XmlMutatorMin.py b/examples/python_mutators/XmlMutatorMin.py new file mode 100644 index 00000000..058b7e61 --- /dev/null +++ b/examples/python_mutators/XmlMutatorMin.py @@ -0,0 +1,331 @@ +#!/usr/bin/python + +""" Mutation of XML documents, should be called from one of its wrappers (CLI, AFL, ...) """ + +from __future__ import print_function +from copy import deepcopy +from lxml import etree as ET +import random, re, io + +########################### +# The XmlMutatorMin class # +########################### + +class XmlMutatorMin: + + """ + Optionals parameters: + seed Seed used by the PRNG (default: "RANDOM") + verbose Verbosity (default: False) + """ + + def __init__(self, seed="RANDOM", verbose=False): + + """ Initialize seed, database and mutators """ + + # Verbosity + self.verbose = verbose + + # Initialize PRNG + self.seed = str(seed) + if self.seed == "RANDOM": + random.seed() + else: + if self.verbose: + print("Static seed '%s'" % self.seed) + random.seed(self.seed) + + # Initialize input and output documents + self.input_tree = None + self.tree = None + + # High-level mutators (no database needed) + hl_mutators_delete = [ "del_node_and_children", "del_node_but_children", "del_attribute", "del_content" ] # Delete items + hl_mutators_fuzz = ["fuzz_attribute"] # Randomly change attribute values + + # Exposed mutators + self.hl_mutators_all = hl_mutators_fuzz + hl_mutators_delete + + def __parse_xml (self, xml): + + """ Parse an XML string. Basic wrapper around lxml.parse() """ + + try: + # Function parse() takes care of comments / DTD / processing instructions / ... + tree = ET.parse(io.BytesIO(xml)) + except ET.ParseError: + raise RuntimeError("XML isn't well-formed!") + except LookupError as e: + raise RuntimeError(e) + + # Return a document wrapper + return tree + + def __exec_among (self, module, functions, min_times, max_times): + + """ Randomly execute $functions between $min and $max times """ + + for i in xrange (random.randint (min_times, max_times)): + # Function names are mangled because they are "private" + getattr (module, "_XmlMutatorMin__" + random.choice(functions)) () + + def __serialize_xml (self, tree): + + """ Serialize a XML document. Basic wrapper around lxml.tostring() """ + + return ET.tostring(tree, with_tail=False, xml_declaration=True, encoding=tree.docinfo.encoding) + + def __ver (self, version): + + """ Helper for displaying lxml version numbers """ + + return ".".join(map(str, version)) + + def reset (self): + + """ Reset the mutator """ + + self.tree = deepcopy(self.input_tree) + + def init_from_string (self, input_string): + + """ Initialize the mutator from a XML string """ + + # Get a pointer to the top-element + self.input_tree = self.__parse_xml(input_string) + + # Get a working copy + self.tree = deepcopy(self.input_tree) + + def save_to_string (self): + + """ Return the current XML document as UTF-8 string """ + + # Return a text version of the tree + return self.__serialize_xml(self.tree) + + def __pick_element (self, exclude_root_node = False): + + """ Pick a random element from the current document """ + + # Get a list of all elements, but nodes like PI and comments + elems = list(self.tree.getroot().iter(tag=ET.Element)) + + # Is the root node excluded? + if exclude_root_node: + start = 1 + else: + start = 0 + + # Pick a random element + try: + elem_id = random.randint (start, len(elems) - 1) + elem = elems[elem_id] + except ValueError: + # Should only occurs if "exclude_root_node = True" + return (None, None) + + return (elem_id, elem) + + def __fuzz_attribute (self): + + """ Fuzz (part of) an attribute value """ + + # Select a node to modify + (rand_elem_id, rand_elem) = self.__pick_element() + + # Get all the attributes + attribs = rand_elem.keys() + + # Is there attributes? + if len(attribs) < 1: + if self.verbose: + print("No attribute: can't replace!") + return + + # Pick a random attribute + rand_attrib_id = random.randint (0, len(attribs) - 1) + rand_attrib = attribs[rand_attrib_id] + + # We have the attribute to modify + # Get its value + attrib_value = rand_elem.get(rand_attrib); + # print("- Value: " + attrib_value) + + # Should we work on the whole value? + func_call = "(?P<func>[a-zA-Z:\-]+)\((?P<args>.*?)\)" + p = re.compile(func_call) + l = p.findall(attrib_value) + if random.choice((True,False)) and l: + # Randomly pick one the function calls + (func, args) = random.choice(l) + # Split by "," and randomly pick one of the arguments + value = random.choice(args.split(',')) + # Remove superfluous characters + unclean_value = value + value = value.strip(" ").strip("'") + # print("Selected argument: [%s]" % value) + else: + value = attrib_value + + # For each type, define some possible replacement values + choices_number = ( \ + "0", \ + "11111", \ + "-128", \ + "2", \ + "-1", \ + "1/3", \ + "42/0", \ + "1094861636 idiv 1.0", \ + "-1123329771506872 idiv 3.8", \ + "17=$numericRTF", \ + str(3 + random.randrange(0, 100)), \ + ) + + choices_letter = ( \ + "P" * (25 * random.randrange(1, 100)), \ + "%s%s%s%s%s%s", \ + "foobar", \ + ) + + choices_alnum = ( \ + "Abc123", \ + "020F0302020204030204", \ + "020F0302020204030204" * (random.randrange(5, 20)), \ + ) + + # Fuzz the value + if random.choice((True,False)) and value == "": + + # Empty + new_value = value + + elif random.choice((True,False)) and value.isdigit(): + + # Numbers + new_value = random.choice(choices_number) + + elif random.choice((True,False)) and value.isalpha(): + + # Letters + new_value = random.choice(choices_letter) + + elif random.choice((True,False)) and value.isalnum(): + + # Alphanumeric + new_value = random.choice(choices_alnum) + + else: + + # Default type + new_value = random.choice(choices_alnum + choices_letter + choices_number) + + # If we worked on a substring, apply changes to the whole string + if value != attrib_value: + # No ' around empty values + if new_value != "" and value != "": + new_value = "'" + new_value + "'" + # Apply changes + new_value = attrib_value.replace(unclean_value, new_value) + + # Log something + if self.verbose: + print("Fuzzing attribute #%i '%s' of tag #%i '%s'" % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag)) + + # Modify the attribute + rand_elem.set(rand_attrib, new_value.decode("utf-8")) + + def __del_node_and_children (self): + + """ High-level minimizing mutator + Delete a random node and its children (i.e. delete a random tree) """ + + self.__del_node(True) + + def __del_node_but_children (self): + + """ High-level minimizing mutator + Delete a random node but its children (i.e. link them to the parent of the deleted node) """ + + self.__del_node(False) + + def __del_node (self, delete_children): + + """ Called by the __del_node_* mutators """ + + # Select a node to modify (but the root one) + (rand_elem_id, rand_elem) = self.__pick_element (exclude_root_node = True) + + # If the document includes only a top-level element + # Then we can't pick a element (given that "exclude_root_node = True") + + # Is the document deep enough? + if rand_elem is None: + if self.verbose: + print("Can't delete a node: document not deep enough!") + return + + # Log something + if self.verbose: + but_or_and = "and" if delete_children else "but" + print("Deleting tag #%i '%s' %s its children" % (rand_elem_id, rand_elem.tag, but_or_and)) + + if delete_children is False: + # Link children of the random (soon to be deleted) node to its parent + for child in rand_elem: + rand_elem.getparent().append(child) + + # Remove the node + rand_elem.getparent().remove(rand_elem) + + def __del_content (self): + + """ High-level minimizing mutator + Delete the attributes and children of a random node """ + + # Select a node to modify + (rand_elem_id, rand_elem) = self.__pick_element() + + # Log something + if self.verbose: + print("Reseting tag #%i '%s'" % (rand_elem_id, rand_elem.tag)) + + # Reset the node + rand_elem.clear() + + def __del_attribute (self): + + """ High-level minimizing mutator + Delete a random attribute from a random node """ + + # Select a node to modify + (rand_elem_id, rand_elem) = self.__pick_element() + + # Get all the attributes + attribs = rand_elem.keys() + + # Is there attributes? + if len(attribs) < 1: + if self.verbose: + print("No attribute: can't delete!") + return + + # Pick a random attribute + rand_attrib_id = random.randint (0, len(attribs) - 1) + rand_attrib = attribs[rand_attrib_id] + + # Log something + if self.verbose: + print("Deleting attribute #%i '%s' of tag #%i '%s'" % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag)) + + # Delete the attribute + rand_elem.attrib.pop(rand_attrib) + + def mutate (self, min=1, max=5): + + """ Execute some high-level mutators between $min and $max times, then some medium-level ones """ + + # High-level mutation + self.__exec_among(self, self.hl_mutators_all, min, max) + diff --git a/examples/python_mutators/common.py b/examples/python_mutators/common.py new file mode 100644 index 00000000..28b8ee80 --- /dev/null +++ b/examples/python_mutators/common.py @@ -0,0 +1,37 @@ +#!/usr/bin/env python +# encoding: utf-8 +''' +Module containing functions shared between multiple AFL modules + +@author: Christian Holler (:decoder) + +@license: + +This Source Code Form is subject to the terms of the Mozilla Public +License, v. 2.0. If a copy of the MPL was not distributed with this +file, You can obtain one at http://mozilla.org/MPL/2.0/. + +@contact: choller@mozilla.com +''' + +from __future__ import print_function +import random +import os +import re + +def randel(l): + if not l: + return None + return l[random.randint(0,len(l)-1)] + +def randel_pop(l): + if not l: + return None + return l.pop(random.randint(0,len(l)-1)) + +def write_exc_example(data, exc): + exc_name = re.sub(r'[^a-zA-Z0-9]', '_', repr(exc)) + + if not os.path.exists(exc_name): + with open(exc_name, 'w') as f: + f.write(data) diff --git a/examples/python_mutators/example.py b/examples/python_mutators/example.py new file mode 100644 index 00000000..d32a7eb2 --- /dev/null +++ b/examples/python_mutators/example.py @@ -0,0 +1,103 @@ +#!/usr/bin/env python +# encoding: utf-8 +''' +Example Python Module for AFLFuzz + +@author: Christian Holler (:decoder) + +@license: + +This Source Code Form is subject to the terms of the Mozilla Public +License, v. 2.0. If a copy of the MPL was not distributed with this +file, You can obtain one at http://mozilla.org/MPL/2.0/. + +@contact: choller@mozilla.com +''' + +import random + +def init(seed): + ''' + Called once when AFLFuzz starts up. Used to seed our RNG. + + @type seed: int + @param seed: A 32-bit random value + ''' + random.seed(seed) + return 0 + +def fuzz(buf, add_buf): + ''' + Called per fuzzing iteration. + + @type buf: bytearray + @param buf: The buffer that should be mutated. + + @type add_buf: bytearray + @param add_buf: A second buffer that can be used as mutation source. + + @rtype: bytearray + @return: A new bytearray containing the mutated data + ''' + ret = bytearray(buf) + # Do something interesting with ret + + return ret + +# Uncomment and implement the following methods if you want to use a custom +# trimming algorithm. See also the documentation for a better API description. + +# def init_trim(buf): +# ''' +# Called per trimming iteration. +# +# @type buf: bytearray +# @param buf: The buffer that should be trimmed. +# +# @rtype: int +# @return: The maximum number of trimming steps. +# ''' +# global ... +# +# # Initialize global variables +# +# # Figure out how many trimming steps are possible. +# # If this is not possible for your trimming, you can +# # return 1 instead and always return 0 in post_trim +# # until you are done (then you return 1). +# +# return steps +# +# def trim(): +# ''' +# Called per trimming iteration. +# +# @rtype: bytearray +# @return: A new bytearray containing the trimmed data. +# ''' +# global ... +# +# # Implement the actual trimming here +# +# return bytearray(...) +# +# def post_trim(success): +# ''' +# Called after each trimming operation. +# +# @type success: bool +# @param success: Indicates if the last trim operation was successful. +# +# @rtype: int +# @return: The next trim index (0 to max number of steps) where max +# number of steps indicates the trimming is done. +# ''' +# global ... +# +# if not success: +# # Restore last known successful input, determine next index +# else: +# # Just determine the next index, based on what was successfully +# # removed in the last step +# +# return next_index diff --git a/examples/python_mutators/simple-chunk-replace.py b/examples/python_mutators/simple-chunk-replace.py new file mode 100644 index 00000000..218dd4f8 --- /dev/null +++ b/examples/python_mutators/simple-chunk-replace.py @@ -0,0 +1,59 @@ +#!/usr/bin/env python +# encoding: utf-8 +''' +Simple Chunk Cross-Over Replacement Module for AFLFuzz + +@author: Christian Holler (:decoder) + +@license: + +This Source Code Form is subject to the terms of the Mozilla Public +License, v. 2.0. If a copy of the MPL was not distributed with this +file, You can obtain one at http://mozilla.org/MPL/2.0/. + +@contact: choller@mozilla.com +''' + +import random + +def init(seed): + ''' + Called once when AFLFuzz starts up. Used to seed our RNG. + + @type seed: int + @param seed: A 32-bit random value + ''' + # Seed our RNG + random.seed(seed) + return 0 + +def fuzz(buf, add_buf): + ''' + Called per fuzzing iteration. + + @type buf: bytearray + @param buf: The buffer that should be mutated. + + @type add_buf: bytearray + @param add_buf: A second buffer that can be used as mutation source. + + @rtype: bytearray + @return: A new bytearray containing the mutated data + ''' + # Make a copy of our input buffer for returning + ret = bytearray(buf) + + # Take a random fragment length between 2 and 32 (or less if add_buf is shorter) + fragment_len = random.randint(1, min(len(add_buf), 32)) + + # Determine a random source index where to take the data chunk from + rand_src_idx = random.randint(0, len(add_buf) - fragment_len) + + # Determine a random destination index where to put the data chunk + rand_dst_idx = random.randint(0, len(buf)) + + # Make the chunk replacement + ret[rand_dst_idx:rand_dst_idx + fragment_len] = add_buf[rand_src_idx:rand_src_idx + fragment_len] + + # Return data + return ret diff --git a/examples/python_mutators/wrapper_afl_min.py b/examples/python_mutators/wrapper_afl_min.py new file mode 100644 index 00000000..df09b40a --- /dev/null +++ b/examples/python_mutators/wrapper_afl_min.py @@ -0,0 +1,117 @@ +#!/usr/bin/env python + +from XmlMutatorMin import XmlMutatorMin + +# Default settings (production mode) + +__mutator__ = None +__seed__ = "RANDOM" +__log__ = False +__log_file__ = "wrapper.log" + +# AFL functions + +def log(text): + """ + Logger + """ + + global __seed__ + global __log__ + global __log_file__ + + if __log__: + with open(__log_file__, "a") as logf: + logf.write("[%s] %s\n" % (__seed__, text)) + +def init(seed): + """ + Called once when AFL starts up. Seed is used to identify the AFL instance in log files + """ + + global __mutator__ + global __seed__ + + # Get the seed + __seed__ = seed + + # Create a global mutation class + try: + __mutator__ = XmlMutatorMin(__seed__, verbose=__log__) + log("init(): Mutator created") + except RuntimeError as e: + log("init(): Can't create mutator: %s" % e.message) + +def fuzz(buf, add_buf): + """ + Called for each fuzzing iteration. + """ + + global __mutator__ + + # Do we have a working mutator object? + if __mutator__ is None: + log("fuzz(): Can't fuzz, no mutator available") + return buf + + # Try to use the AFL buffer + via_buffer = True + + # Interpret the AFL buffer (an array of bytes) as a string + if via_buffer: + try: + buf_str = str(buf) + log("fuzz(): AFL buffer converted to a string") + except: + via_buffer = False + log("fuzz(): Can't convert AFL buffer to a string") + + # Load XML from the AFL string + if via_buffer: + try: + __mutator__.init_from_string(buf_str) + log("fuzz(): Mutator successfully initialized with AFL buffer (%d bytes)" % len(buf_str)) + except: + via_buffer = False + log("fuzz(): Can't initialize mutator with AFL buffer") + + # If init from AFL buffer wasn't succesful + if not via_buffer: + log("fuzz(): Returning unmodified AFL buffer") + return buf + + # Sucessful initialization -> mutate + try: + __mutator__.mutate(max=5) + log("fuzz(): Input mutated") + except: + log("fuzz(): Can't mutate input => returning buf") + return buf + + # Convert mutated data to a array of bytes + try: + data = bytearray(__mutator__.save_to_string()) + log("fuzz(): Mutated data converted as bytes") + except: + log("fuzz(): Can't convert mutated data to bytes => returning buf") + return buf + + # Everything went fine, returning mutated content + log("fuzz(): Returning %d bytes" % len(data)) + return data + +# Main (for debug) + +if __name__ == '__main__': + + __log__ = True + __log_file__ = "/dev/stdout" + __seed__ = "RANDOM" + + init(__seed__) + + in_1 = bytearray("<foo ddd='eeee'>ffff<a b='c' d='456' eee='ffffff'>zzzzzzzzzzzz</a><b yyy='YYY' zzz='ZZZ'></b></foo>") + in_2 = bytearray("<abc abc123='456' abcCBA='ppppppppppppppppppppppppppppp'/>") + out = fuzz(in_1, in_2) + print(out) + |