Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skillsnpx agentmods add skills/ricneves-ai/flowgrammers-skills/ai-securityWrote 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/ricneves-ai/flowgrammers-skills/ai-security)<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/ai-security"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/ai-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/skills/ricneves-ai/flowgrammers-skills/ai-security"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/ai-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 | $0.00075 | $0.04989 |
| Opus 5 | $0.00037 | $0.02495 |
| Sonnet 5 | $0.00015 | $0.00998 |
| Haiku 4.5 | $0.00007 | $0.00499 |
Grade A, and why
ai-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 8d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Segurança em IA
Skill de avaliação de segurança em IA e LLM para detectar injeção de prompt, vulnerabilidades de jailbreak, risco de inversão de modelo, exposição a envenenamento de dados e abuso de ferramentas por agents. Esta skill NÃO cobre segurança geral de aplicações (veja security-pen-testing) ou detecção de anomalias comportamentais em infraestrutura (veja threat-detection) — esta skill trata especificamente da avaliação de segurança de sistemas de IA/ML e agents baseados em LLM.
Sumário
- Visão Geral
- Ferramenta de Escaneamento de Ameaças em IA
- Detecção de Injeção de Prompt
- Avaliação de Jailbreak
- Risco de Inversão de Modelo
- Risco de Envenenamento de Dados
- Abuso de Ferramentas por Agent
- Cobertura MITRE ATLAS
- Padrões de Design de Guardrail
- Fluxos de Trabalho
- Anti-Padrões
- Referências Cruzadas
Visão Geral
O que Esta Skill Faz
Esta skill fornece a metodologia e ferramentas para avaliação de segurança em IA/ML — escaneamento de assinaturas de injeção de prompt, pontuação de risco de inversão de modelo e envenenamento de dados, mapeamento de resultados para técnicas MITRE ATLAS e recomendação de controles de guardrail. Suporta LLMs, classificadores e modelos de embedding.
Distinção de Outras Skills de Segurança
| Skill | Foco | Abordagem |
|---|---|---|
| ai-security (esta) | Segurança de sistemas IA/ML | Especializada — injeção em LLM, inversão de modelo, mapeamento ATLAS |
| security-pen-testing | Vulnerabilidades de aplicação | Geral — OWASP Top 10, segurança de API, escaneamento de dependências |
| red-team | Simulação de adversários | Ofensiva — planejamento de kill-chain contra infraestrutura |
| threat-detection | Anomalias comportamentais | Proativa — caça em telemetria, não em entradas de modelo |
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.
- 8d ago First seen · 367 lines · 75 tokens per session scan A 8b443b3360e8
ai-security is a skill published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 4,989 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…