Skip to main content
skill CX Codex

competition-agent-cloud — Claude Code skill: install

The competition-agent-cloud Claude Code skill investigates agent and cloud paths in CTF sandboxes. It is routed in after the orchestrator sets the sandbox assumptions, for tracing input-to-tool actions or deployment behavior.

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-agent-cloud -a claude-code
Open on GitHub

What competition-agent-cloud does

The skill examines CTF challenges involving AI agents, cloud infrastructure, and build or release chains. It traces how untrusted content reaches a model-visible instruction and triggers a tool action. It also compares deployment configuration with live system state and artifact provenance.

It starts by choosing an agent-led or infrastructure-led path, then maps a minimal evidence chain. $ctf-sandbox-orchestrator must first establish sandbox assumptions, node ownership, and evidence priorities. For narrower topics, the workflow points to dedicated skills. Replies default to Simplified Chinese unless English is requested.

What it helps with

  • trace untrusted content from model context to a tool action
  • compare deployment manifests with live mounts and environment
  • follow a dependency from source through build to runtime use
  • connect CI steps to published artifacts consumed by a service

Example prompts for the agent

  • Trace how untrusted retrieved text leads to a tool call in this sandbox challenge.
  • Compare the Kubernetes manifests with the running application's mounts and environment.
  • Follow this dependency from source through publication to the running service.

How to install competition-agent-cloud

1Skills CLI (Vercel)

npx skills add zhaoxuya520/reverse-skill --skill competition-agent-cloud -a claude-code

2Manually: put the files in place

~/.claude/skills/competition-agent-cloud/SKILL.md

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

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

Questions about competition-agent-cloud

How do I install competition-agent-cloud in Claude Code?

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

What does competition-agent-cloud do?

It investigates agent and cloud CTF scenarios, tracing untrusted input to tool actions and comparing deployment configuration with live infrastructure.

What does competition-agent-cloud require?

$ctf-sandbox-orchestrator must establish the sandbox assumptions, node ownership, and evidence priorities before routing a task here.

Source text

SKILL.md · MIT
---
name: competition-agent-cloud
description: Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for AI-agent, prompt-injection, MCP or toolchain, cloud, container, CI/CD, and supply-chain challenges. Use when the user asks to analyze prompt-to-tool flows, retrieval poisoning, mounted secrets, deployment drift, runtime-vs-manifest mismatches, registry provenance, or CI-produced artifacts under sandbox assumptions. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
---

# Competition Agent Cloud

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 path is driven by prompt-to-tool execution, retrieval and memory boundaries, deployment drift, or build and release provenance.

Reply in Simplified Chinese unless the user explicitly requests English.

## Quick Start

1. Decide whether the dominant path is agentic or infrastructure-driven.
2. Map one minimal control chain: untrusted input -> visible context -> tool or deployment side effect.
3. Distinguish checked-in intent from live runtime truth.
4. Keep prompts, tool args, manifests, mounts, and provenance steps in compact evidence blocks.
5. Reproduce the exploit or misconfiguration with minimal context and minimal instrumentation.

## Workflow

### 1. Agent And Prompt Injection

- Treat prompts, tool schemas, retrieved chunks, planner notes, memory files, and handoffs as challenge artifacts.
- Prove one minimal chain from untrusted content to model-visible instruction to tool side effect.
- Distinguish claimed capability from runtime-exposed capability.

### 2. Cloud, Containers, And CI/CD

- Split build-time, deploy-time, and runtime.
- Reconcile compose or kube manifests with live mounts, env, logs, and traffic.
- Trace provenance from source to dependency resolution to build to publish to runtime consumer.

## Read This Reference

- Load `references/agent-cloud.md` for the control-stack checklist, deployment-truth checklist, and evidence packaging.
- If the task is specifically about prompt-boundary abuse or retrieved-content-to-tool drift, prefer `$competition-prompt-injection`.
- If the task is specifically about CI, dependency provenance, registry drift, or shipped artifacts, prefer `$competition-supply-chain`.
- If the task is specifically about queue payloads, async worker drift, retries, or worker-only runtime state, prefer `$competition-queue-worker-drift`.
- If the task is specifically about SSRF to internal control surfaces, metadata endpoints, or metadata-derived token pivots, prefer `$competition-ssrf-metadata-pivot`.
- If the task is specifically about proxy-upstream parse differentials, ambiguous headers, path normalization drift, or request smuggling behavior, prefer `$competition-request-normalization-smuggling`.
- If the task is specifically about metadata-service access, instance or workload identity, link-local token paths, or metadata-derived privilege, prefer `$competition-cloud-metadata-path`.
- If the task is specifically about kube API permissions, service-account trust, admission behavior, controller drift, or cluster secret exposure, prefer `$competition-k8s-control-plane`.
- If the task is specifically about live mounts, sidecars, init containers, or runtime-only secret exposure, prefer `$competition-container-runtime`.
- If the task is specifically about container-to-host boundary crossing, kernel-surface prerequisites, or escape primitive verification, prefer `$competition-kernel-container-escape`.

## What To Preserve

- Prompt snippets, retrieved chunks, planner transitions, and final tool args
- Compose or Kubernetes fragments tied to live mounts or routes
- Artifact hashes, dependency drift, CI steps, and the resulting runtime consumer

© zhaoxuya520 · MIT · zhaoxuya520/reverse-skill

Similar skills

All skills for Security →
cloud-sync thedotmack This Claude Code skill connects claude-mem to cmem.ai Pro and checks sync status. It runs on requests to set up cloud sync, sync memories, or check a backup. CX Codex +1 2,600installs competition-zip-archive freyrswift competition-zip-archive is a Claude Code skill that recovers legacy ZipCrypto keys from archives using known-plaintext attacks. CTF workflows trigger it after ctf-sandbox-orchestrator runs. CX Codex +1 ★ 71repo stars huawei-cloud-iam-query huaweicloud huawei-cloud-iam-query queries Huawei Cloud IAM users, groups, agencies, and AK/SK keys using a read-only Python SDK. Useful for inspecting access policies and security settings. CX Codex +1 18,300installs google-cloud-storage-bucket-architect official google google-cloud-storage-bucket-architect is a Claude Code skill that plans and creates Google Cloud Storage buckets with workload and security settings. It activates for requests to create a bucket for an app, service, pipeline, or dataset. CX Codex +1 2,800installs aws-cloud-architecture manutej aws-cloud-architecture is a Claude Code skill for planning and configuring AWS infrastructure across compute, storage, security, serverless services, and costs. CX Codex +1 600installs analyzing-cloud-storage-access-patterns mahipal analyzing-cloud-storage-access-patterns — a Claude Code skill that reads CloudTrail Data Events, GCS audit logs and Azure Storage Analytics to flag after-hours bulk downloads, fresh source IPs and GetObject spikes. CX Codex +1 578installs

From the same set36

The whole set →
competition-stego-media The competition-stego-media Claude Code skill searches media files for hidden payloads in CTF tasks. It runs after ctf-sandbox-orchestrator routes an image, audio, video, or document for steganography analysis. CX Codex +1 110installs competition-ios-runtime competition-ios-runtime — a skill for Claude Code that automates iOS runtime analysis and hooking. It runs as a downstream module after $ctf-sandbox-orchestrator is active. CX Codex +1 110installs competition-graphql-rpc-drift competition-graphql-rpc-drift — a Claude Code skill compares GraphQL and RPC contracts with live handler behavior. It joins a CTF workflow after the main orchestrator sets up the sandbox. CX Codex +1 110installs competition-identity-windows competition-identity-windows — a skill for Claude Code and Codex that examines Active Directory attacks, Windows host artifacts, and CTF pivot chains. It runs after routing by $ctf-sandbox-orchestrator. CX Codex +1 109installs competition-browser-persistence competition-browser-persistence — a skill for Claude Code that investigates browser persistence surfaces in CTF sandboxes. It activates when stored client state alters request flows, rendering, or access rules. CX Codex +1 109installs competition-ad-certificate-abuse The competition-ad-certificate-abuse Claude Code skill traces certificate-based abuse in AD CS CTF sandboxes. It is triggered by questions about templates, enrollment rights, PKINIT, and privilege paths through certificates. CX Codex +1 109installs competition-reverse-pwn competition-reverse-pwn is a Claude Code skill for binary and vulnerability analysis in CTF challenges. After $ctf-sandbox-orchestrator is active, it inspects dumps and verifies exploit chains. CX Codex +1 109installs competition-supply-chain The competition-supply-chain Claude Code skill traces artifact provenance from source to runtime. It is routed after ctf-sandbox-orchestrator when a challenge involves dependency drift, CI, builds, or releases. CX Codex +1 109installs

Project sponsors

Companies that keep this analytics open