Competition Prompt Injection logo

Competition Prompt Injection

CommunityPopular
zhaoxuya520
competition-prompt-injection

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Overview

Publisherzhaoxuya520
Repositoryreverse-skill
Skill namecompetition-prompt-injection
Stars
36.3K
Forks
5K
Bundled files
2
LicenseMIT
Links
Skill sourceRepository
  • 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 Prompt Injection 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-prompt-injection .claude/skills/competition-prompt-injection
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competition Prompt Injection 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 Prompt Injection 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 Prompt Injection 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 Prompt Injection

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

Use this skill when the challenge is primarily about trust boundaries inside an agentic system.

Reply in Simplified Chinese unless the user explicitly requests English.

Quick Start

  1. Identify the first untrusted content that becomes model-visible.
  2. Map the chain from retrieval, memory, or transcript into planner or executor behavior.
  3. Record the exact point where text becomes a tool argument, file path, network target, or secret request.
  4. Prove one minimal exploit chain before exploring variants.
  5. Keep prompt snippets and tool transitions in compact evidence blocks.

Workflow

1. Map The Control Stack

  • Track system, developer, user, retrieved, memory, planner, and tool-response layers separately.
  • Distinguish claimed capability from runtime-exposed capability.
  • Note what the model can actually call, read, or mutate.

2. Prove The Boundary Crossing

  • Reproduce one chain from untrusted text to changed planner behavior, changed tool args, or secret exposure.
  • Keep the decisive transcript compact: source chunk, rewritten planner state, final tool invocation.
  • Prefer the smallest transcript that still demonstrates the bug.

3. Report By Boundary

  • State which layer failed: retrieval, summarizer, planner, executor, tool normalization, or output post-processing.
  • Separate instruction drift from actual side effect.

Read This Reference

  • Load references/prompt-injection.md for the checklist, evidence layout, and common prompt-boundary pitfalls.

What To Preserve

  • Original malicious chunk or prompt
  • Intermediate summary or planner drift if it matters
  • Final tool args, file paths, or exposed secret surface

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 Prompt Injection AI skill do?

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Why use Competition Prompt Injection on TypingMind?

Because you install it once and use it with any model. Competition Prompt Injection 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 Prompt Injection in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhaoxuya520/reverse-skill/tree/main/CTF-Sandbox-Orchestrator/competition-prompt-injection. 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 Prompt Injection?

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 Prompt Injection?

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

Is the Competition Prompt Injection 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.

Related AI Skills

View all
affaan-m logo

Frontend Patterns

affaan-m
CommunityPopular

Patrones de desarrollo frontend para React, Next.js, gestión de estado, optimización de rendimiento y buenas prácticas de UI.

39.1K
261.1K
Instructions
View
affaan-m logo

Golang Patterns

affaan-m
CommunityPopular

Patrones idiomáticos de Go, buenas prácticas y convenciones para construir aplicaciones Go robustas, eficientes y mantenibles.

39.1K
261.1K
Instructions
View
affaan-m logo

Golang Testing

affaan-m
CommunityPopular

Patrones de pruebas Go incluyendo pruebas basadas en tablas, subpruebas, benchmarks, fuzzing y cobertura de código. Sigue la metodología TDD con prácticas idiomáticas de Go.

39.1K
261.1K
Instructions
View
affaan-m logo

Jpa Patterns

affaan-m
CommunityPopular

Patrones JPA/Hibernate para diseño de entidades, relaciones, optimización de consultas, transacciones, auditoría, indexación, paginación y pooling en Spring Boot.

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

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