Skip to content
Get packs

Competition Relay Coercion Chain

Traces forced-auth coercion and NTLM relay paths in a CTF sandbox, step by step.

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

What it does

This is a specialist add-on for an AI agent working on capture-the-flag (CTF) security competitions in a sandboxed lab. Once it is active, the agent organizes an attack-style analysis into a chain: what forces a machine to authenticate, where that authentication is relayed, which service accepts it, and what privilege or artifact results. It is written to run only after a parent skill (ctf-sandbox-orchestrator) has set up the sandbox assumptions, and it tells the agent to reply in Simplified Chinese unless English is requested.

Great for

  • Security students or players practising for CTF competitions in an isolated lab
  • Red-team trainers building reproducible lab exercises on forced authentication and relay concepts

Skip it if

  • Testing real networks, systems or accounts you do not own or have written authorisation to test, because the skill is built to trace relay and coercion attack paths that can cause real harm outside a sandbox
  • Users looking for a general security checklist or defensive hardening guide, since it focuses on exploitation paths rather than defence

Try asking

  • “Trace which service accepts a relayed NTLM authentication in our sandbox lab”
  • “Map the coercion source, relay target and resulting privilege for this CTF box”
  • “Determine whether a forced-auth trigger can lead to certificate enrollment in the lab”
Step-by-step guide: how to use Competition Relay Coercion ChainInstall, 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-relay-coercion-chain.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip competition-relay-coercion-chain.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip competition-relay-coercion-chain.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

  • Only use it inside a sandbox or competition environment you are authorised to test, and state the scope in your first message
  • Start with the parent orchestrator skill so the sandbox assumptions are set before this skill is routed in

What's inside

  • agents/openai.yaml
  • references/relay-coercion-chain.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.