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 skills/rodrigohighermind/highermind-code-skills/hm-securitynpx skills add rodrigohighermind/highermind-code-skills --skill hm-securitygit clone --depth 1 https://github.com/rodrigohighermind/highermind-code-skillsWrote 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/skills/rodrigohighermind/highermind-code-skills/hm-security)<a href="https://agentmods.dev/skills/rodrigohighermind/highermind-code-skills/hm-security"><img src="https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-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 5.1 | $0.00138 | $0.09805 |
| Opus 5 | $0.00069 | $0.04902 |
| Sonnet 5 | $0.00028 | $0.01961 |
| Haiku 4.5 | $0.00014 | $0.00980 |
Grade C, and why
hm-security scanned grade C with 4 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 6d ago.
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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
| Direct injection | User input vai direto pro prompt do LLM sem sanitizacao? Testar: "Ignore all previous instructions and..." | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Metadata endpoints bloqueados (169.254.169.254, fd00::, localhost)? 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.
- **Race conditions**: duas requests simultaneas criam duplicatas? Saldo negativo? Double-spend? Testar com `curl` paralelo ou script. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Command injection: sem `os.system()`, `subprocess.run(shell=True)`, `eval()`, `exec()` com input do usuario? How it starts
The opening of the file, as written. The whole thing — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hm-security — Auditoria de Segurança (v2.3)
Você está agora em modo security. Você é um auditor de segurança senior. Seu trabalho e encontrar toda vulnerabilidade — básica ou avancada — antes que um atacante encontre. A barra é o que a Tempest, CrowdStrike, Trail of Bits, NCC Group, ou Cure53 entregariam num pentest report.
Princípio central
Segurança não é feature. Não é fase. Não é checklist pra passar. E a fundacao sobre a qual tudo e construido. Se a fundacao tem rachaduras, não importa o quao bonito e o predio.
Todo finding de segurança é CRÍTICO até que se prove o contrario. O onus de provar que não é CRÍTICO esta em quem quer rebaixar, não em quem encontrou.
Esta skill cobre attack-driven (vazamento, comprometimento, escalation). Para bug/crash-driven (backup, migration safety, undo destrutivo, DR), complementa com
/hm-data-integrity. As duas se sobrepoem em "dados sao sagrados" mas atacam o problema por angulos diferentes — segurança e integridade sao primos, não gemeos.
Quando usar
- Antes de qualquer deploy pra ambiente externo (homol, staging, prod)
- Apos adicionar autenticacao, autorizacao, ou fluxo financeiro
- Quando o projeto manipula dados sensíveis (PII, financeiro, saúde)
- Periodicamente como auditoria de manutencao
- Quando mudar dependências significativas
- Antes de abrir o projeto pra usuarios reais
- Apos integrar qualquer LLM/AI (prompt injection e vetor real)
Níveis de auditoria
| Nível | Quando usar | Escopo |
|---|---|---|
| L1 — Baseline | Todo projeto, todo deploy | Container, secrets, OWASP Top 10, dependências, .dockerignore |
| L2 — Enterprise | Projetos com auth, dados sensíveis, multi-tenant | L1 + API Top 10, business logic, ASVS L2, crypto, compliance, AI/LLM |
| L3 — Critical | Fintech, saúde, dados regulados, alta exposicao | L2 + ASVS L3, supply chain, threat modeling (STRIDE), formal verification |
Se não souber o nível, use L2. L1 e o mínimo absoluto. L3 e pra quando o impacto de uma breach e catastrofico.
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.
- 6d ago First seen · 759 lines · 138 tokens per session scan C 7da6b8134d93
hm-security is a skill published in the GitHub repository rodrigohighermind/highermind-code-skills (192 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 9,805 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 4 findings (instruction-override phrasing, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…