Segurança

ISO/IEC 42001:2023 AI Management System (AIMS) specialist for compliance teams running internal audits. Three decisions: (1) Where are the gaps against Clauses 4-10 and what do we close first? (2) What goes in the AI risk register and which Annex A controls treat each risk? (3) What's the 12-month internal audit plan that satisfies Clause 9.2? Use when preparing for certification, scoping internal

Prepare sistematicamente um repositório ou projeto para lançamento público ou de código aberto. Isso inclui a prontidão pré-código aberto, sanitização do repositório, criação de documentação essencial (READMEs, licenças), endurecimento do .gitignore, verificações de conteúdo sensível e prontidão para CI/lançamento.

Comprehensive macOS development environment health check. Detects brew drift, orphaned packages, security issues, version mismatches, and deferred cleanup readiness.

Read-only audit dispatch for the active feature on the requested axis — security (OWASP, trust boundary, secrets), perf (measure-first, N+1, CWV), or simplify (Chesterton's Fence, deletion test). Use when the user says "security review", "is this safe", "is this fast enough", "perf check", "N+1", "simplify this", "Chesterton's Fence". Not for write actions or whole-project audits.

OpenClaw and NemoClaw operations — sandbox management, inference provider config, policy configuration, Tailscale integration, security hardening, skill vetting. Trigger on: "OpenClaw", "NemoClaw", "OpenShell", "sandbox", "openclaw tui", "agent assistant", "ClawHub", "gateway token", or any task involving the personal AI assistant deployment on node_primary.

Scanner de segurança com IA — detecta vulnerabilidades, segredos vazados e riscos de dependência em qualquer base de código.

Service-profile-driven project audit. Auto-fires when the user requests audit, review, code review, pre-launch check, security audit, OWASP/SOLID/12-Factor compliance, project skeleton/bootstrap/setup, or any equivalent in any language (e.g., 점검, 감사, 리뷰, 출시 전 검토, 보안 점검, 골조, 셋업). Reads the full 0–10 section checklist from SPEC.md, filters items by grade (🔴🟠🟡🔵⚪) against the user's service profil

Auxilia em auditorias de segurança de contratos inteligentes Cairo na Starknet, incluindo revisão de vulnerabilidades, modelagem de ameaças e criação de testes de segurança snforge.

Explain or apply a general operating model that turns messy requests and unfamiliar domains into reusable, adopted capabilities through clarification, context engineering, reuse, composition, hardening, and adoption.

Review a genai.recipe.yml or compiled skill bundle for security issues — unsafe tools, network access, hardcoded secrets, overly broad permissions. Use when the user asks for a security review or audit of a Genai skill.

Comprehensive security audit: detects insecure defaults, hardcoded secrets, sharp edges, supply chain risks, and OWASP vulnerabilities. Based on Trail of Bits methodology. Use when auditing security, reviewing config, or pre-deployment checks. For PR diffs, use /security-review instead.

Realiza revisões de código completas com feedback acionável e priorizado. Abrange correção, segurança, desempenho, legibilidade e melhores práticas em diversas linguagens.