Playbook de injeção de prompt em LLMs. Use ao testar aplicações de IA/LLM quanto a injeção direta, indireta via RAG/navegação, abuso de ferramentas, exfiltração de dados, riscos de segurança MCP e técnicas de bypass de defesas.
O playbook yaklang/llm-prompt-injection é um guia completo para testar vulnerabilidades de injeção de prompt em aplicações baseadas em grandes modelos de linguagem (LLMs). Ele cobre cenários de ataque como injeção direta (manipulação do prompt do usuário), injeção indireta (exploração de fontes de dados externas, como RAG ou navegação web), abuso de ferramentas (ex.: forçar o modelo a executar ações não autorizadas), exfiltração de dados (ex.: roubo de informações sensíveis via saída do modelo) e riscos de segurança em protocolos como MCP (Model Context Protocol). Além disso, inclui técnicas para contornar defesas comuns, como filtros de entrada e restrições de saída. Baseado na documentação SKILL.md, ele é útil para desenvolvedores e especialistas em segurança que desejam identificar e mitigar esses riscos em plataformas como Claude Code, Cursor e Codex. O playbook fornece exemplos práticos, diretrizes de teste e recomendações de mitigação, sendo essencial para avaliações de segurança de aplicações de IA.
npx skills add https://github.com/yaklang/hack-skills/tree/main/skills/llm-prompt-injectionInstalled? Explore more Produtividade e Colaboração skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
Playbook de injeção de prompt em LLMs. Use ao testar aplicações de IA/LLM quanto a injeção direta, injeção indireta via RAG/navegação, abuso de ferramentas, exfiltração de dados, riscos de segurança MCP e técnicas de bypass de defesas.
This repo contains 20 individual skills — each has its own dedicated page.
401/403 bypass playbook. Use when encountering access-denied responses on admin panels, API endpoints, or restricted paths. Covers path manipulation, HTTP method tampering, header injection, protocol downgrade, and automated bypass tools.
Active Directory ACL abuse playbook. Use when exploiting misconfigured AD permissions including GenericAll, WriteDACL, DCSync rights, shadow credentials, LAPS reading, GPO abuse, and BloodHound-guided attack paths.
AD Certificate Services attack playbook. Use when targeting misconfigured AD CS for privilege escalation via ESC1-ESC13 template abuse, NTLM relay to enrollment, CA officer abuse, and certificate-based persistence.
Kerberos attack playbook for Active Directory. Use when targeting AD authentication via AS-REP roasting, Kerberoasting, golden/silver/diamond tickets, delegation abuse, or pass-the-ticket attacks.
AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
Android pentesting playbook. Use when testing Android applications for SSL pinning bypass, exported component abuse, WebView vulnerabilities, intent redirection, root detection bypass, tapjacking, and backup extraction during authorized mobile security assessments.
Anti-debugging detection and bypass playbook. Use when reversing protected binaries that detect debuggers via ptrace, PEB flags, timing checks, or signal/exception handlers on Linux and Windows.
API authentication and JWT abuse playbook. Use when testing bearer tokens, API keys, claim trust, header spoofing, rate limits, and API auth boundary weaknesses.
API authorization and BOLA testing playbook. Use when APIs expose object identifiers, nested resources, hidden writable fields, or weak function-level authorization.
API reconnaissance and documentation review playbook. Use when discovering endpoints, schemas, versions, OpenAPI specs, hidden docs, and surface area for API testing.
Entry P1 category router for API security. Use when choosing between API recon, authorization, token abuse, and hidden-parameter workflows before any deeper API topic skill.
Arbitrary write to RCE playbook. Use when you have an arbitrary write primitive (from heap exploitation, format string, or OOB write) and need to convert it into code execution by targeting GOT, hooks, _IO_FILE vtable, exit_funcs, TLS_dtor_list, modprobe_path, .fini_array, or C++ vtables.
Authentication bypass testing playbook. Use when assessing login flows, password reset logic, account recovery, MFA bypass, token predictability, brute-force resistance, and session boundary flaws.
Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill.
Binary protection bypass playbook. Use when identifying and bypassing ASLR, PIE, NX/DEP, stack canary, RELRO, FORTIFY_SOURCE, CET, and MTE protections in ELF binaries to enable exploitation.
Browser and V8 exploitation playbook. Use when exploiting JavaScript engine vulnerabilities including JIT type confusion, incorrect bounds elimination, and V8 sandbox bypass to achieve renderer RCE and sandbox escape in Chrome/Chromium.
Entry P1 category router for business logic testing. Use when workflow abuse, race conditions, pricing flaws, or multi-step state attacks matter more than parser-level input injection.
Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.
Classical cipher analysis playbook. Use when encountering substitution ciphers, Vigenere, transposition, XOR, or encoded text in CTF challenges that requires frequency analysis, Kasiski examination, or known-plaintext cryptanalysis.
Clickjacking playbook. Use when testing whether target pages can be framed, whether X-Frame-Options or CSP frame-ancestors are properly configured, and whether UI redress attacks can trigger sensitive actions.
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.