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
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/competition-prompt-injection/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/competition-prompt-injection/
1Skills CLI (Vercel)
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a codex2Manually: put the files in place
.agents/skills/competition-prompt-injection/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a cursor2Manually: put the files in place
.cursor/skills/competition-prompt-injection/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install zhaoxuya520/reverse-skill CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md2Manually: put the files in place
.github/skills/competition-prompt-injection/SKILL.md1Skills CLI (Vercel)
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a gemini-cli2Platform CLI
gemini skills install https://github.com/zhaoxuya520/reverse-skill --path CTF-Sandbox-Orchestrator/competition-prompt-injectionManually: put the files in place
.devin/skills/competition-prompt-injection/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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