repo-forensics MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

18 scanners covering distinct threat surfaces
Skill-specific: SKILL.md poisoning, Unicode smuggling, OpenClaw patterns
MCP-specific: tool poisoning, rug-pull enablers
Correlation engine connects findings across scanners to catch compound attacks
Zero dependencies — pure audit, safe to run on anything

Demo ao vivo

Como fica na prática

repo-forensics-skill.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

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

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

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add repo-forensics-skill -- git clone https://github.com/alexgreensh/repo-forensics ~/.claude/skills/repo-forensics

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: repo-forensics

Audit a third-party skill before you clone it into ~/.claude/skills

👤 Anyone installing skills from strangers on GitHub ⏱ ~15 min beginner

Quando usar: Someone sent you a cool-looking skill link. Before clone, you want to know if it's safe.

Pré-requisitos

repo-forensics installed — git clone https://github.com/alexgreensh/repo-forensics ~/.claude/skills/repo-forensics

Fluxo

Point at the target repo URL

Use repo-forensics. Scan https://github.com/<author>/<skill> with the skill_threats, secrets, dataflow, and lifecycle scanners. Report findings.✓ Copiado

→ Per-scanner report with severity flags
Read correlated findings

Any correlations across scanners — e.g. a secret-leak path plus a lifecycle hook?✓ Copiado

→ Correlation summary

Resultado: A go / no-go decision grounded in scanner output, not vibes.

Armadilhas

Trusting a green scan as full proof of safety — Scanners are strong floor, not a ceiling — still read SKILL.md

Combine com: github · filesystem

Audit an MCP server for tool poisoning and rug-pull patterns

👤 Teams onboarding a new MCP into a production agent stack ⏱ ~20 min intermediate

Quando usar: Before adding a new MCP server to an agent with real permissions.

Fluxo

Run MCP-focused scanners

Scan this MCP server repo with mcp_security, skill_threats, integrity, and dast.✓ Copiado

→ Findings focused on tool descriptions and install scripts
Check git history for identity spoofing

Run git_forensics on the same repo — any spoofed commits?✓ Copiado

→ Author / signing analysis

Resultado: An MCP security dossier before you wire it into your agent.

Run post-incident scanners after a suspicious install

👤 Anyone who just ran npm/pip install and feels uneasy ⏱ ~15 min intermediate

Quando usar: Install finished with unexpected behavior; you want to know if something landed.

Fluxo

Run post_incident + entropy scans

Run post_incident scanner on ~/.npm and the current project. Also entropy scan the installed packages.✓ Copiado

→ Flags for suspicious cached artifacts or encoded payloads

Resultado: Evidence of whether to rotate secrets and rebuild.

Armadilhas

Running scans from the potentially-compromised shell — Run from a fresh shell or another machine when in doubt

Combinações

Combine com outros MCPs para 10× de alavancagem

repo-forensics-skill + github

Pull a PR's diff and scan only the added files

Fetch PR #123 and run repo-forensics just on the files it adds.✓ Copiado

repo-forensics-skill + filesystem

Scan a locally cloned repo and save a JSON report

Scan ./suspicious-repo and write findings.json next to it.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar
skill_threats	repo path	Any skill audit
mcp_security	repo path	MCP audits
secrets	repo path	Always
dataflow	repo path	Suspicious egress concerns
lifecycle	repo path	Pre-install
git_forensics	repo path	Checking maintainer identity
entropy	repo path	Obfuscation suspected
sast	repo path	General code risk

Custo e limites

O que custa rodar

Cota de API: None
Tokens por chamada: Moderate — scanner output summarization can grow
Monetário: Free
Dica: Run only the scanners relevant to the threat model (skills → skill_threats; MCP → mcp_security)

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: None — scanner is read-only

Saída de dados: Local-only by default

Nunca conceda: Write access to the repo under audit

This is a defensive tool. Don't use scanner output to stress-test your own targets — it's not a pentest kit.

Solução de problemas

Erros comuns e correções

Scanner reports 0 findings on obviously sketchy repo

Ensure you ran against the full repo path, not a subset; check scanner selection

Verificar: repo-forensics list-scanners

False positives flood the report

Filter by severity; focus on high/critical; use correlation to prioritize

Alternativas

repo-forensics vs. outros

Alternativa	Quando usar	Troca
claude-cybersecurity	Your code needs OWASP-style app security review rather than supply-chain vetting	Different focus — app logic vs install-time threats
gitleaks / trufflehog	You only need secret scanning	Single-scanner, not correlation

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills