Competition Zip Archive logo

Competition Zip Archive

CommunityPopular
zhaoxuya520
competition-zip-archive

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Use when the user asks to solve an encrypted ZIP challenge, inspect ZipCrypto metadata, recover keys from a known file prefix, or unlock an archive without starting with password brute force. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Overview

Publisherzhaoxuya520
Repositoryreverse-skill
Skill namecompetition-zip-archive
Stars
36.3K
Forks
5K
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zhaoxuya520 on GitHub. Read the source before you install it.

Installation

Install the Competition Zip Archive AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhaoxuya520/reverse-skill.git /tmp/reverse-skill
mkdir -p .claude/skills
cp -r /tmp/reverse-skill/CTF-Sandbox-Orchestrator/competition-zip-archive .claude/skills/competition-zip-archive
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competition Zip Archive in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Competition Zip Archive on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Competition Zip Archive is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Competition ZIP Archive

Use this skill only as a downstream specialization after $ctf-sandbox-orchestrator is active and has established sandbox assumptions, evidence priorities, and the analysis project root. If that has not happened yet, return to $ctf-sandbox-orchestrator first.

Use this skill when the decisive path is an encrypted ZIP/PKZIP archive rather than an upload parser or a generic crypto blob. Prefer the legacy ZipCrypto known-plaintext path when the challenge gives a predictable file, format header, template, or other recoverable plaintext. Do not begin with blind password brute force.

Reply in Simplified Chinese unless the user explicitly requests English. Keep commands and tool output in their original form.

Quick Start

  1. Preserve the original archive, compute a hash, and work on a copy under the analysis project's work/<case>/ directory.
  2. Confirm the actual archive format and list entries before attempting a password attack.
  3. Determine whether the entry uses legacy ZipCrypto. bkcrack does not recover WinZip AES or other modern encryption.
  4. Build an exact known-plaintext candidate. The attack needs at least 12 known plaintext bytes, including at least 8 contiguous bytes.
  5. Recover the internal keys with bkcrack, then create an unencrypted copy and extract it.
  6. Preserve the command, entry names, known-plaintext source, recovered keys, output hash, and final flag as evidence.

Tool Setup

Use the normal tool index and bootstrap path before guessing an executable location:

powershell
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/refresh-tool-index.ps1
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/bootstrap-reverse.ps1 -Capability bkcrack

On Kali, use the equivalent capability command:

bash
bash kali/scripts/bootstrap-reverse.sh bkcrack

The Windows capability is pinned to the v1.8.1 release and verifies the GitHub asset digest. If the tool is installed manually, refresh skills/tool-index.md afterward.

Workflow

1. Establish Archive Truth

Keep the original immutable and record:

bash
sha256sum challenge.zip
file challenge.zip
bkcrack -L challenge.zip

On Windows, use Get-FileHash in place of sha256sum. bkcrack -L shows entry names, compression methods, and encryption status. Do not infer the encryption type from the .zip extension alone.

Check the entry that will provide the known plaintext. A useful candidate is a stored or otherwise predictable file such as a PNG, PDF, text template, or challenge-generated configuration. A local ZIP header (PK\x03\x04) is metadata for the archive entry, not plaintext inside the encrypted member, so it is not by itself a useful known-plaintext sample.

2. Recover Keys With Known Plaintext

When the ciphertext entry is flag.txt and a matching plaintext entry is available in known.zip:

bash
bkcrack -C challenge.zip -c flag.txt -P known.zip -p flag.txt

For raw ciphertext and plaintext files:

bash
bkcrack -c cipherfile -p plainfile

The plaintext must match the bytes represented in the encrypted entry. If the entry was deflated, an uncompressed copy of the file is not automatically the right input; use a matching ZIP fixture or the exact compressed bytes.

If the known bytes begin at an offset, add -o <offset>. If only 8-11 bytes are contiguous, combine them with other known bytes using sparse hints:

bash
bkcrack -c cipherfile -p plainfile -x 25 4b4f -x 30 21

The successful run yields three internal ZipCrypto keys. Record them exactly as printed; they are not the original password.

3. Unlock And Validate

Use the recovered keys to make a new archive, leaving the source untouched:

bash
bkcrack -C challenge.zip -k K0 K1 K2 -D unlocked.zip
7z t unlocked.zip
7z x unlocked.zip -ounpacked

Replace K0 K1 K2 with the hexadecimal values printed by bkcrack. Validate the output with the archive test command and a hash or exact flag comparison. If only one raw member is needed, -d can write its deciphered bytes; deflated raw data may need the inflate.py helper shipped with bkcrack.

4. Re-route When Preconditions Fail

  • WinZip AES or another modern encryption mode: stop this path and identify the challenge-specific primitive.
  • No reliable known plaintext: inspect filenames, metadata, compression choices, challenge source, and other entries before considering password recovery.
  • Known plaintext shorter than the requirement: locate more contiguous bytes or use evidence-backed sparse offsets.
  • The problem is an application upload/parser chain: hand off to $competition-file-parser-chain.
  • The problem is a generic ciphertext or custom cipher after archive extraction: hand off to $competition-crypto-mobile.

Evidence To Preserve

  • Original and working-copy paths plus SHA-256 hashes
  • bkcrack -L output and the selected encrypted member
  • Exact plaintext fixture, compression method, offsets, and sparse byte hints
  • Key recovery command and the three recovered internal keys
  • unlocked.zip validation output, extraction path, and final artifact hash

Read references/zip-archive.md for the decision table and evidence checklist.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Competition Zip Archive AI skill do?

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Use when the user asks to solve an encrypted ZIP challenge, inspect ZipCrypto metadata, recover keys from a known file prefix, or unlock an archive without starting with password brute force. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Why use Competition Zip Archive on TypingMind?

Because you install it once and use it with any model. Competition Zip Archive is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Competition Zip Archive in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhaoxuya520/reverse-skill/tree/main/CTF-Sandbox-Orchestrator/competition-zip-archive. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Competition Zip Archive?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Competition Zip Archive?

As many as you like. As long as a model supports skills, you can use Competition Zip Archive with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Competition Zip Archive AI skill free?

Yes. It is published on GitHub by zhaoxuya520 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇