AGENT SKILL

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.

License 许可
MIT
最近更新
2026-10-15
Stars
★ 42
Forks
24

01 前言 Front Matter

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.

02 资源文件 2

03 SKILL.md 正文

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

04 同仓库更多 Skills

longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

yingan-tuoxiu

Owner-authorized YingAn/YingPo Android APK shell rehydration and stable rebuild workflow. Use for APKs with tiny or abnormal root DEX files, v.m.p or abcd655xx shell callbacks, libabcd/lib*shellservice_dex native loaders, protected assets, runtime-loaded DEX images, hidden real Application or Activity routes, and native lifecycle wrappers that must be recovered into a normally installable, signed multidex APK without changing product authentication or business authorization behavior.

★ 42
longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

reverse-engineering

Use when performing reverse engineering on any target: websites, desktop binaries (PE/ELF), mobile apps (APK/IPA), or network protocols. Covers web scraping/API reverse, disassembly and decompilation, Frida/Xposed hooking, il2cpp/Unity reverse, protocol capture and replay, encryption/signature analysis, and memory debugging. Triggers: 逆向、反编译、Hook、脱壳、抓包、协议分析、Frida、Xposed、il2cpp、Unity逆向、 内存扫描、DLL注入、PE分析、ELF分析、APK逆向、IPA逆向、反混淆、签名分析、加密还原、 smali、Ghidra、IDA、Cheat Engine、mitmproxy、Wireshark、脱壳、加固、SO逆向、Web逆向。

★ 42
longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

game-hacking

游戏辅助开发全链路助手——覆盖内存读写、协议分析、反编译、Hook 技术、驱动级隐藏、自动化脚本。 支持 C/C++、Python、x86/x64 汇编、DirectX/OpenGL。适用于 PC 端游、Android/iOS 手游、主机游戏。 当用户提到以下任何关键词时必须触发:游戏外挂、游戏辅助、内存修改、CE教程、游戏Hook、 协议分析、反编译、驱动隐藏、游戏脚本、按键精灵、游戏逆向、内存扫描、指针追踪、DLL注入、 游戏破解、脱壳、抓包分析、Frida、Xposed、il2cpp、Unity逆向、UE4逆向、DirectX Hook、 OpenGL Hook、游戏自动化、坐标识别、模板匹配、游戏安全测试。

★ 42
longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

supply-chain-security

暂无简介

★ 42
longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

reverse-engineering

Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

★ 42
longwangjiang88
longwangjiang88/SusuAIOverclock-pojia

radare2

Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.

★ 42