Skip to main content
skill CX Codex

competition-prompt-injection — Claude Code skill: analysis and install

The competition-prompt-injection Claude Code skill examines CTF challenges involving trust boundaries in agent systems. It traces how untrusted content can alter planner behavior, tool arguments, or expose secrets.

MIT 109 installs ★ 45,047 updated 2026-09-22

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a claude-code
Open on GitHub

What competition-prompt-injection does

The skill analyzes CTF challenges where trust breaks between parts of an agent system. It follows content from retrieval, memory, or a transcript into planner and executor behavior, then distinguishes instruction changes from an actual side effect.

The workflow starts by locating the first untrusted text the model can see. It traces that input to a changed tool argument, file path, network target, or secret request. The skill calls for proving one minimal chain and preserving the key evidence: the original content, any relevant planner change, and the final tool call.

Findings are grouped by the layer that failed, such as retrieval, summarization, planning, execution, tool normalization, or output post-processing. references/prompt-injection.md contains the checklist and evidence layout. This skill is only used after $ctf-sandbox-orchestrator has set the sandbox assumptions, node ownership, and evidence priorities.

What it helps with

  • trace untrusted content through to a tool invocation
  • locate the agent layer where a trust boundary fails
  • separate instruction drift from an actual side effect
  • capture concise evidence of secret exposure

Example prompts for the agent

  • Analyze a CTF challenge where retrieved text changes a tool argument.
  • Trace how memory content affects the planner and its tool call.
  • Find the layer in this agent chain that exposes a secret.

How to install competition-prompt-injection

1Skills CLI (Vercel)

npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a claude-code

2Manually: put the files in place

~/.claude/skills/competition-prompt-injection/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/competition-prompt-injection/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about competition-prompt-injection

How do I install competition-prompt-injection in Claude Code?

Run npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a claude-code. The skill file is at ~/.claude/skills/competition-prompt-injection/SKILL.md.

What does competition-prompt-injection do?

It analyzes CTF challenges about prompt injection and trust failures in agent systems. The workflow connects untrusted input to planner changes, altered tool arguments, or secret exposure.

What must happen before competition-prompt-injection is used?

$ctf-sandbox-orchestrator must first establish the sandbox assumptions, node ownership, and evidence priorities. This skill is routed in afterward.

Source text

SKILL.md · MIT
---
name: competition-prompt-injection
description: 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.
---

# 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

© zhaoxuya520 · MIT · zhaoxuya520/reverse-skill

Similar skills

All skills for Security →

From the same set36

The whole set →
competition-oauth-oidc-chain competition-oauth-oidc-chain is a Claude Code skill for mapping OAuth/OIDC chains, redirects, and token exchanges after the CTF sandbox orchestrator establishes base assumptions. CX Codex +1 109installs competition-file-parser-chain The competition-file-parser-chain Claude Code skill follows a file from upload to a parser or deserializer. It runs after ctf-sandbox-orchestrator routes a file-processing investigation to it. CX Codex +1 109installs competition-firmware-layout competition-firmware-layout — a skill for Claude Code, Codex, Cursor and other platforms that maps firmware images, partition tables, and boot chains. CX Codex +1 109installs competition-windows-pivot The competition-windows-pivot Claude Code skill traces host-to-host movement in Windows CTF scenarios. It connects recovered credentials or tickets to the service that accepted them. CX Codex +1 109installs competition-kerberos-delegation competition-kerberos-delegation — a skill for Claude Code that automates Kerberos delegation analysis in CTF scenarios. It runs after context setup via $ctf-sandbox-orchestrator to verify exploitation paths. CX Codex +1 109installs competition-relay-coercion-chain The competition-relay-coercion-chain Claude Code skill traces forced-authentication and relay chains in a CTF sandbox. It runs when an analysis needs to identify the service accepting relayed credentials and the resulting effect. CX Codex +1 109installs competition-mailbox-abuse competition-mailbox-abuse — a skill for Claude Code and other environments specializing in analyzing enterprise mail abuse within CTF sandboxes. CX Codex +1 109installs competition-malware-config competition-malware-config — a skill for Claude Code and other platforms recovers malware configurations, decodes C2 beacon parameters, and extracts IOCs. CX Codex +1 109installs

Project sponsors

Companies that keep this analytics open