repo-forensics MCP — 使用场景, 安装 & 实时演示

为什么要用

核心特性

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

实时演示

实际使用效果

repo-forensics-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/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
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.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 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

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
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "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
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

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

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

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

加入 context_servers。Zed 保存后热重载。

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

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： repo-forensics

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

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

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

前置条件

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

步骤

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.✓ 已复制

→ Per-scanner report with severity flags
Read correlated findings

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

→ Correlation summary

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

注意事项

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

搭配使用： 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

何时使用： Before adding a new MCP server to an agent with real permissions.

步骤

Run MCP-focused scanners

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

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

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

→ Author / signing analysis

结果： 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

何时使用： Install finished with unexpected behavior; you want to know if something landed.

步骤

Run post_incident + entropy scans

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

→ Flags for suspicious cached artifacts or encoded payloads

结果： Evidence of whether to rotate secrets and rebuild.

注意事项

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

组合

与其他 MCP 搭配，撬动十倍杠杆

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.✓ 已复制

repo-forensics-skill + filesystem

Scan a locally cloned repo and save a JSON report

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

工具

此 MCP 暴露的能力

工具	输入参数	何时调用
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

成本与限制

运行它的成本

API 配额: None
每次调用 Token 数: Moderate — scanner output summarization can grow
费用: Free
提示: Run only the scanners relevant to the threat model (skills → skill_threats; MCP → mcp_security)

安全

权限、密钥、影响范围

凭据存储： None — scanner is read-only

数据出站： Local-only by default

切勿授予： 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.

故障排查

常见错误与修复

Scanner reports 0 findings on obviously sketchy repo

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

验证： repo-forensics list-scanners

False positives flood the report

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

替代方案

repo-forensics 对比其他方案

替代方案	何时用它替代	权衡
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

repo-forensics

为什么要用

核心特性

实时演示

实际使用效果

安装

选择你的客户端

使用场景

实战用法： repo-forensics

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

前置条件

步骤

注意事项

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

步骤

Run post-incident scanners after a suspicious install

步骤

注意事项

组合

与其他 MCP 搭配，撬动十倍杠杆

工具

此 MCP 暴露的能力

成本与限制

运行它的成本

安全

权限、密钥、影响范围

故障排查

常见错误与修复

替代方案

repo-forensics 对比其他方案

更多

资源