Skip to content
Get packs

Competition Reverse Pwn

Guides an agent through CTF-style reverse engineering, malware triage, and exploit work inside an assumed sandbox

Source Download skill
Repository
zhaoxuya520/reverse-skill
Stars
43,969
Licence
MIT
Files
3 files

What it does

This skill gives an AI agent a structured method for binary-heavy security challenges: reverse engineering programs, unpacking samples, analysing memory dumps or packet captures, debugging crashes, and building or checking exploit chains. It is a downstream specialist meant to be used only after a parent skill, ctf-sandbox-orchestrator, has set up sandbox assumptions. It tells the agent to keep original artifacts untouched, work from passive triage first, and record evidence such as offsets, hashes and crash state, and it points to other specialist skills for narrower topics.

Great for

  • Security students working on CTF reverse engineering or pwnable challenges in an isolated lab
  • Analysts triaging malware samples or firmware in a controlled sandbox environment
  • Developers learning how exploit primitives and crash analysis are documented and verified

Skip it if

  • Attacking systems you do not own or have written permission to test, since the skill assumes a sandbox and gives no legal or scope check
  • Use outside the parent orchestrator workflow, because the skill itself says it should only run after that skill has set sandbox assumptions
  • General software development or everyday binary tasks that do not involve security analysis

Try asking

  • “Reverse this ELF binary and tell me what its main function checks before printing the flag”
  • “Unpack this sample and list its imports, sections and entropy without modifying the original file”
  • “Debug this crash, record the faulting offset and registers, and reproduce it from a clean baseline”
  • “Help me build and verify a ret2libc chain for this pwnable challenge in my local sandbox”
Step-by-step guide: how to use Competition Reverse PwnInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    competition-reverse-pwn.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip competition-reverse-pwn.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip competition-reverse-pwn.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run it inside an isolated VM or container, and make sure the parent orchestrator has set sandbox boundaries first
  • Ask the agent to keep the original sample, decoded layers and instrumented copies as separate files
  • Note that replies default to Simplified Chinese unless you explicitly ask for English

What's inside

  • agents/openai.yaml
  • references/reverse-pwn.md
  • SKILL.md

Redistributed unmodified from zhaoxuya520/reverse-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.