Borrowing it
Nothing to install: this file belongs to dewtech-technologies/tubemind-secure-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dewtech-technologies/tubemind-secure-mcp/main/.claude/commands/dare-security.mdgit clone --depth 1 https://github.com/dewtech-technologies/tubemind-secure-mcpWrote 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/commands/dewtech-technologies/tubemind-secure-mcp/dare-security)<a href="https://agentmods.dev/commands/dewtech-technologies/tubemind-secure-mcp/dare-security"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/dare-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/dewtech-technologies/tubemind-secure-mcp/dare-security"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/dare-security.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01816 |
| Opus 5.5 | $0.00000 | $0.00726 |
| Sonnet 5.5 | $0.00000 | $0.00363 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
dare-security scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to dare-security — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dare-security
Guia completo de segurança para todas as fases do DARE. Use para: revisar o DESIGN/BLUEPRINT com foco em segurança, implementar controles em uma task específica, ou auditar o projeto existente.
Como usar
/dare-security # auditoria geral do projeto
/dare-security task-005 # revisar segurança de uma task específica
/dare-security design # revisar DARE/DESIGN.md com lente de segurança
/dare-security deps # auditar dependências vulneráveis agora
Aplicação por fase
/dare-security design — Revisar DESIGN.md
Leia DARE/DESIGN.md e verifique:
- Seção RS-* com requisitos de segurança numerados existe
- RS-01 (validação de entrada), RS-02 (hash/criptografia), RS-03 (controle de acesso), RS-04 (auditoria de deps), RS-05 (secrets) presentes
- Riscos de segurança identificados com mitigações (SSRF, Injection, Auth bypass...)
- Fora do escopo não omite itens de segurança críticos para v1
/dare-security deps — Auditar dependências
Execute o comando de auditoria da stack do projeto:
# Detectar stack automaticamente e rodar
npm audit --audit-level=high # se package.json presente
cargo audit # se Cargo.toml presente
pip-audit # se requirements.txt / pyproject.toml presente
composer audit # se composer.json presente
govulncheck ./... # se go.mod presente
Critério: CVE HIGH ou CRITICAL = reportar ao usuário com versão afetada, CVE ID e versão corrigida disponível. Propor o fix (bump de versão ou substituição de pacote).
Auto-fix quando seguro:
npm audit fix # Node — corrige sem breaking changes
cargo update # Rust — bumpa dentro das constraints do Cargo.toml
pip install --upgrade [pacote] # Python — atualizar pacote específico
OWASP Top 10 — Referência Rápida por Stack
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 · 233 lines · 0 tokens per session scan A d4587f301676
dare-security is a command published in the GitHub repository dewtech-technologies/tubemind-secure-mcp (0 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,816 tokens. A static security scan graded it A with 0 findings. It is 100% identical to dare-security, differing in 0 lines, and is treated as a copy.
dare-security compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dare-securitydewtech-technologies/tubemind-secure-mcp | Command | 0 | today | MIT | A | 0 | Claude Code |
| test-suitetravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 7 | Claude Code |
| pull-repostravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 13 | Claude Code |
| security-scantravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 6 | Claude Code |
| assemble-teamtravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 25 | Claude Code |
| standardize-claude-mdtravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 18 | Claude Code |
| helptravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 9 | Claude Code |