Name: competition-prompt-injection
Author: zhaoxuya520

Imported from zhaoxuya520/reverse-skill (CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md). Install upstream with npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection. Copyright stays with the author.

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

Identify the first untrusted content that becomes model-visible.
Map the chain from retrieval, memory, or transcript into planner or executor behavior.
Record the exact point where text becomes a tool argument, file path, network target, or secret request.
Prove one minimal exploit chain before exploring variants.
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

Install competition-prompt-injection and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zhaoxuya520-reverse-skill-competition-prompt-injection", "kind": "skill", "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 `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.", "publisher": "zhaoxuya520", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/zhaoxuya520/reverse-skill", "path": "CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md", "ref": "HEAD", "url": "https://github.com/zhaoxuya520/reverse-skill/blob/HEAD/CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md", "key": "zhaoxuya520/reverse-skill/CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md" } }, "instructions": "# Competition Prompt Injection\n\nUse 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.\n\nUse this skill when the challenge is primarily about trust boundaries inside an agentic system.\n\nReply in Simplified Chinese unless the user explicitly requests English.\n\n## Quick Start\n\n1. Identify the first untrusted content that becomes model-visible.\n2. Map the chain from retrieval, memory, or transcri", "cost": { "context_tokens": 492 } }

competition-prompt-injection

About