Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/dewtech-technologies/dare-method/skill-securitygit clone --depth 1 https://github.com/dewtech-technologies/dare-methodWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-security)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-security"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-security.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02410 | $0.02410 |
| Opus 5 | $0.01205 | $0.01205 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade B, and why
skill-security scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Bloqueie acesso a metadados de cloud (`169.254.169.254`) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Verificar manualmente ou com curl: How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diretrizes de Segurança DARE
Você é um Especialista em AppSec. Garanta que Design → Blueprint → Tasks → Execução sigam rigorosamente as práticas a seguir.
Aplicação nas Fases do DARE
Fase 1 — Design (/generate-design / /dare-design)
- Requisitos de segurança obrigatórios (seção RS-*):
- RS-01: validação de entrada (OWASP A03)
- RS-02: hash de senhas / proteção de dados sensíveis (OWASP A02)
- RS-03: controle de acesso por recurso (OWASP A01)
- RS-04: auditoria de dependências sem CVE HIGH/CRITICAL (OWASP A06)
- RS-05: secrets via variáveis de ambiente — nunca em código
- Identifique vetores de ataque na ideia inicial e adicione mitigações em Riscos
Fase 2 — Architect (/generate-blueprint / /dare-blueprint)
- Endpoints da API: inclua coluna
Auth(JWT/apiKey/público) e middleware de rate limiting - Modelo de dados: marque campos sensíveis (PII, tokens, hashes) e como são protegidos
- Fases do plano: inclua Fase N-1 = Auditoria de Segurança e Dependências com critério de DONE explícito
- Validation gates por stack devem incluir o comando de auditoria de dependências
Fase 3 — Tasks (/generate-tasks)
- Toda task que adiciona dependência externa → validation gate inclui
npm audit/cargo audit/pip-audit/composer audit - Crie task dedicada para: headers de segurança HTTP, rate limiting, scan de secrets
- Seção "Considerações de Segurança" obrigatória em cada
EXECUTION/task-*.md
Fase 4 — Execute (/execute-task)
Aplique as proteções abaixo ao implementar qualquer código.
OWASP Top 10 — Implementação
A01 — Broken Access Control
- Verifique permissão no recurso, não só na rota:
user.can('update', post)/authorize('update', $post)/check_permission(user, resource) - Princípio do menor privilégio: tokens têm escopos mínimos necessários
- Nunca exponha IDs sequenciais em URLs para recursos privados — use UUID ou ULID
- Multi-tenant: sempre filtre por
tenant_id/org_idem toda query
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 246 lines · 2,410 tokens per session scan B b8842a44431a
skill-security is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,410 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
hedgehog
Hedgehog build discipline — how to work in this repo.
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
observability
Observability Standards — Logging, Tracing & Metrics.
api-design
REST API Design Standards Agent.
pr-standards
Git Commit & PR Standards for AI-Assisted Development.