competition-prompt-injection
starsforks
How to install competition-prompt-injection?
zhaoxuya520/reverse-skill/competition-prompt-injection
$npx -y skills add zhaoxuya520/reverse-skill --skill competition-prompt-injectionInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieva
SKILL.md
| 1 | # Competition Prompt Injection |
| 2 | |
| 3 | Use this skill only as a downstream specialization after `$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. |
| 4 | |
| 5 | Use this skill when the challenge is primarily about trust boundaries inside an agentic system. |
| 6 | |
| 7 | Reply in Simplified Chinese unless the user explicitly requests English. |
| 8 | |
| 9 | ## Quick Start |
| 10 | |
| 11 | 1. Identify the first untrusted content that becomes model-visible. |
| 12 | 2. Map the chain from retrieval, memory, or transcript into planner or executor behavior. |
| 13 | 3. Record the exact point where text becomes a tool argument, file path, network target, or secret request. |
| 14 | 4. Prove one minimal exploit chain before exploring variants. |
| 15 | 5. Keep prompt snippets and tool transitions in compact evidence blocks. |
| 16 | |
| 17 | ## Workflow |
| 18 | |
| 19 | ### 1. Map The Control Stack |
| 20 | |
| 21 | - Track system, developer, user, retrieved, memory, planner, and tool-response layers separately. |
| 22 | - Distinguish claimed capability from runtime-exposed capability. |
| 23 | - Note what the model can actually call, read, or mutate. |
| 24 | |
| 25 | ### 2. Prove The Boundary Crossing |
| 26 | |
| 27 | - Reproduce one chain from untrusted text to changed planner behavior, changed tool args, or secret exposure. |
| 28 | - Keep the decisive transcript compact: source chunk, rewritten planner state, final tool invocation. |
| 29 | - Prefer the smallest transcript that still demonstrates the bug. |
| 30 | |
| 31 | ### 3. Report By Boundary |
| 32 | |
| 33 | - State which layer failed: retrieval, summarizer, planner, executor, tool normalization, or output post-processing. |
| 34 | - Separate instruction drift from actual side effect. |
| 35 | |
| 36 | ## Read This Reference |
| 37 | |
| 38 | - Load `references/prompt-injection.md` for the checklist, evidence layout, and common prompt-boundary pitfalls. |
| 39 | |
| 40 | ## What To Preserve |
| 41 | |
| 42 | - Original malicious chunk or prompt |
| 43 | - Intermediate summary or planner drift if it matters |
| 44 | - Final tool args, file paths, or exposed secret surface |
People who liked this also viewed
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API perSkillsJul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: SkillsJul 2026
- azure-rbacOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
- better-auth-best-practicesAgent skill from better-auth/skillsSkillsJul 2026
- firebase-security-rules-auditorA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.SkillsJul 2026
- audit-websiteAudit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-opSkillsJul 2026
