genpark-agentic-smart-contract-vulnerability-static-sentinel-skill

Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)

Autonomous Web3 Smart Contract Vulnerability Static Sentinel. Audits EVM Solidity code for critical security flaws (reentrancy state changes, unhandled external calls, unchecked delegatecall, tx.origin authentication vulnerabilities) and outputs risk audit reports.

🌐 Official GenPark AI Ecosystem Links

• GenPark Official Website: https://www.genpark.ai

• LinkedIn Official Page: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)

Related MCP server: solidity-sentinel

🌟 Key Features

• 100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.

• Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.

• Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.

• Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.

🚀 Quick Start

1. Direct Python SDK Usage

from client import AgenticSmartContractVulnerabilityStaticSentinel

def main():
    sentinel = AgenticSmartContractVulnerabilityStaticSentinel()
    solidity_code = """
    function transferOwnership(address newOwner) public {
        require(tx.origin == owner, "Not owner");
        owner = newOwner;
    }
    """
    res = sentinel.audit_contract_code("OwnableLegacy", solidity_code)
    print("--- Smart Contract Security Audit ---")
    print(f"Contract: {res['contract_name']} | Verdict: {res['audit_verdict']}")
    for v in res['vulnerabilities_detected']:
        print(f"* [{v['severity']}] {v['vulnerability_id']}: {v['title']} - {v['description']}")

if __name__ == "__main__":
    main()

2. Run as Model Context Protocol (MCP) Server

Start standard JSON-RPC 2.0 server over stdio:

python mcp_server.py

Execute embedded test harness:

python mcp_server.py --test

🛠️ MCP Tool Specification

Inspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.

📜 License & Community

Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550