Trail of Bits Skills MCP — Сценарии использования, Установка & Живое демо

Name: Trail of Bits Skills MCP Server
Author: trailofbits

Зачем использовать

Ключевые функции

Written by a security firm, not a hobbyist — patterns reflect real incidents
Covers C/C++, Rust, Solidity, Python, Go, TypeScript
Defensive-only: audit/review flows, not offensive tooling
Modular — pull individual skills without adopting the whole bundle
CC-BY-SA-4.0 licensed, attribution required

Живое демо

Как выглядит на практике

готово

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "trailofbits-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/trailofbits/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "trailofbits-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/trailofbits/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "trailofbits-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/trailofbits/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "trailofbits-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/trailofbits/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "trailofbits-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/trailofbits/skills",
        "~/.claude/skills/skills"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "trailofbits-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/trailofbits/skills",
          "~/.claude/skills/skills"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add trailofbits-skill -- git clone https://github.com/trailofbits/skills ~/.claude/skills/skills

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: Trail of Bits Skills

Add a security-review pass to every PR

👤 Teams without a dedicated security engineer ⏱ ~30 min intermediate

Когда использовать: Your PRs currently go straight from code-review to merge — no security eyes.

Предварительные требования

Skills installed — git clone https://github.com/trailofbits/skills ~/.claude/skills/trailofbits

Поток

Scope the diff

Use trailofbits/pr-review skill on the current PR. List files the skill thinks are security-relevant with reasons.✓ Скопировано

→ Concrete file-by-file relevance reasons
Deep review

For each flagged file, run the appropriate domain skill (crypto, input-validation, auth). Report findings with severity.✓ Скопировано

→ Severity-ranked list with code refs
Summary for reviewer

Write a 5-bullet PR comment summarizing the findings, non-scary but precise.✓ Скопировано

→ Reviewer-friendly summary with exact line citations

Итог: A security review comment on every PR that catches real issues without drowning you in false positives.

Подводные камни

Skill flags style issues as security — Calibrate by prompting: "focus on exploitable issues only"

Сочетать с: github · filesystem

Audit cryptographic code paths in a service

👤 Devs maintaining auth/encryption code ⏱ ~90 min advanced

Когда использовать: You have a JWT/HMAC/encryption layer and want someone smart to double-check.

Поток

Find crypto

Use trailofbits/crypto-review. Scan /src for files that touch crypto APIs. Report them.✓ Скопировано

→ Crypto call-site inventory
Audit each

For each site: what algorithm? Key management? Nonce reuse risk? IV handling? Cite source.✓ Скопировано

→ Per-site audit with code refs
Remediation plan

For any medium+ finding, draft a remediation — concrete code change, not "consider using ...".✓ Скопировано

→ Applicable diffs, not vague advice

Итог: A crypto audit report with concrete fixes, from a baseline of common mistakes ToB has seen in real engagements.

Подводные камни

Not a substitute for a real audit — Use for self-review; hire professionals before launch of high-value surfaces

Сочетать с: github

Комбинации

Сочетайте с другими MCP — эффект x10

trailofbits-skill + github

Post findings as a PR review comment

Post the review as a PR comment — severities as labels.✓ Скопировано

trailofbits-skill + filesystem

Scan the whole repo offline

Run the full security sweep across /src and write report to /audit/report.md.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать
scope_review	diff\|path	Before deep dive
crypto_review	path	Crypto code specifically
input_validation_review	path	API/boundary code
iac_review	path	Terraform / CloudFormation / K8s manifests

Стоимость и лимиты

Во что обходится

Квота API: N/A
Токенов на вызов: Review is reading-heavy; budget proportional to diff size
Деньги: Free (CC-BY-SA)
Совет: Scope first — don't run deep skills on irrelevant files

Безопасность

Права, секреты, радиус поражения

Минимальные скоупы: filesystem-read

Хранение учётных данных: None

Исходящий трафик: None from skill; reviewed code is in your LLM context

Никогда не давайте: write access unless auto-remediating

Not a replacement for a formal security audit — use it to catch the obvious before paying for experts

Устранение неполадок

Частые ошибки и исправления

Skill flags safe code as vulnerable

Ask for rationale; if weak, dismiss with reason. Calibration improves over sessions.

Misses obvious bugs

The skill codifies Trail of Bits' patterns — if your stack is unusual (e.g. niche Rust crate), it may miss. Add custom patterns.

Outputs too long to review

Constrain: "top 5 highest-severity findings only"

Альтернативы

Trail of Bits Skills в сравнении

Альтернатива	Когда использовать	Компромисс
Semgrep rules	You want static analysis in CI, not interactive review	Narrower pattern set; no LLM reasoning
CodeQL	You want deep dataflow analysis	Much more setup; not a skill

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills