Trail of Bits Skills MCP — Cas d'usage, Installer & Démo en direct

Name: Trail of Bits Skills MCP Server
Author: trailofbits

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

prêt

Installer

Choisissez votre client

~/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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : Trail of Bits Skills

Add a security-review pass to every PR

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

Quand l'utiliser : Your PRs currently go straight from code-review to merge — no security eyes.

Prérequis

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

Déroulement

Scope the diff

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

→ 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.✓ Copié

→ Severity-ranked list with code refs
Summary for reviewer

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

→ Reviewer-friendly summary with exact line citations

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

Pièges

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

Combiner avec : github · filesystem

Audit cryptographic code paths in a service

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

Quand l'utiliser : You have a JWT/HMAC/encryption layer and want someone smart to double-check.

Déroulement

Find crypto

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

→ Crypto call-site inventory
Audit each

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

→ Per-site audit with code refs
Remediation plan

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

→ Applicable diffs, not vague advice

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

Pièges

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

Combiner avec : github

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

trailofbits-skill + github

Post findings as a PR review comment

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

trailofbits-skill + filesystem

Scan the whole repo offline

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
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

Coût et limites

Coût d'exécution

Quota d'API: N/A
Tokens par appel: Review is reading-heavy; budget proportional to diff size
Monétaire: Free (CC-BY-SA)
Astuce: Scope first — don't run deep skills on irrelevant files

Sécurité

Permissions, secrets, portée

Portées minimales : filesystem-read

Stockage des identifiants : None

Sortie de données : None from skill; reviewed code is in your LLM context

Ne jamais accorder : write access unless auto-remediating

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

Dépannage

Erreurs courantes et correctifs

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"

Alternatives

Trail of Bits Skills vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills