Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

TL;DR

Knowdit is a knowledge-driven framework that improves smart contract vulnerability detection by leveraging shared DeFi semantics and an agentic multi-step auditing process, significantly outperforming baselines.

Contribution

It introduces a novel knowledge graph from audit reports and an agentic multi-agent system for systematic vulnerability detection in DeFi smart contracts.

Findings

Detects all high-severity vulnerabilities in tested projects.

Identifies 12 new high- and 10 medium-severity vulnerabilities in real-world projects.

Outperforms baseline methods in vulnerability detection accuracy.

Abstract

Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic. We observe that recurring vulnerabilities across diverse DeFi business models often share the same underlying economic mechanisms, which we term DeFi semantics, and that capturing these shared abstractions can enable more systematic auditing. Building on this insight, we propose Knowdit, a knowledge-driven, agentic framework for smart contract vulnerability detection. Knowdit first constructs an auditing knowledge graph from historical human audit reports, linking fine-grained DeFi semantics with recurring vulnerability patterns. Given a new project, a multi-agent framework leverages this knowledge through an iterative loop of specification generation, harness synthesis, fuzz execution, and finding reflection, driven by a shared working memory for continuous refinement. We evaluate Knowdit on 12 recent Code4rena projects with 75 ground-truth vulnerabilities. Knowdit detects all 14 high-severity and 77\% of medium-severity vulnerabilities with only 2 false positives, significantly outperforming all baselines. Applied to six real-world projects, Knowdit further discovers 12 high- and 10 medium-severity previously unknown vulnerabilities, proving its outstanding performance.