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 skills add yanis7774/mac-security-audit-skill --skill mac-security-auditgit clone --depth 1 https://github.com/yanis7774/mac-security-audit-skillWrote 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/yanis7774/mac-security-audit-skill/mac-security-audit)<a href="https://agentmods.dev/skills/yanis7774/mac-security-audit-skill/mac-security-audit"><img src="https://agentmods.dev/badge/skills/yanis7774/mac-security-audit-skill/mac-security-audit/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/yanis7774/mac-security-audit-skill/mac-security-audit"><img src="https://agentmods.dev/badge/skills/yanis7774/mac-security-audit-skill/mac-security-audit.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 | $0.00324 | $0.00854 |
| Opus 5 | $0.00162 | $0.00427 |
| Sonnet 5 | $0.00065 | $0.00171 |
| Haiku 4.5 | $0.00032 | $0.00085 |
Grade B, and why
mac-security-audit 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 9d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
а TCC.db — Full Disk Access у терминала. Если sudo недоступен (неинтерактивно) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
signatures, plaintext secrets (.env/.netrc/.aws/shell history — paths only), Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
macOS Security Audit
Аудит безопасности macOS: запуск read-only сбора + осмысленный разбор находок.
Шаги
-
Запусти ядро — скрипт
mac-security-audit.shлежит рядом с этим SKILL.md, в директории скилла (ничего не меняет в системе):bash "<директория-этого-скилла>/mac-security-audit.sh"Скрипт пишет Markdown-отчёт на Рабочий стол и выводит путь в конце.
-
Прочитай отчёт и проведи триаж по
docs/CHECKS.md. Для каждой секции — что норма, что требует внимания. Интерпретируй, не пересказывай сырой вывод. -
Sudo / TCC. Часть проверок (pf, список профилей конфигурации) требует sudo, а TCC.db — Full Disk Access у терминала. Если sudo недоступен (неинтерактивно) или нет FDA — дай пользователю точные команды для запуска в его терминале; не пытайся обойти защиту.
Правила безопасности (соблюдать строго)
- Скрипт только читает — не добавляй в него изменяющих команд.
- Ничего деструктивного без явного подтверждения пользователя.
- Перед фиксом объясни: что меняется, что может сломаться, как откатить
(откаты в
docs/CHECKS.md). - Перед удалением сертификатов/ключей — бэкап.
- Не запрашивай и не логируй пароли/passphrase.
- Не публикуй отчёт — в нём приватные данные. Делиться можно только скриптом.
Формат ответа
Сводка (критичных/предупреждений) → разбор по приоритету (🔴→🟡→🟢) с рисками простым языком и фиксами → чек-лист ручных действий (sudo/GUI/TCC) в конце.
Полный справочник «норма / подозрительно / фикс с откатом» — в docs/CHECKS.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 62 lines · 324 tokens per session scan B 32795ff6f663
mac-security-audit is a skill published in the GitHub repository yanis7774/mac-security-audit-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 324 tokens to every session and 854 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…