WalletGuard is a LangGraph agent that fans out blockchain + security tools (RPC, honeypot.is, GoPlus, explorer verification, bytecode heuristics, OKX Web3), then uses Claude (or heuristic fallback)
AI agents are starting to hold wallets, sign transactions, and move funds on their own — but they're doing it without any shared sense of risk. A single honeypot token or an unlimited approve call is enough to drain a wallet, and right now there's no common layer an agent can check before it acts. Humans have Etherscan tabs and gut instinct; agents have nothing.
SecurityGuard is our answer: a security layer built for agents, not people. It's an AI-powered risk oracle that any wallet, trading bot, or DeFi agent can call before signing — sending back a simple, machine-readable verdict: Approve, Warn, or Block, backed by a calibrated risk score and a clear explanation.
Under the hood it's a LangGraph agent that pulls from multiple blockchain and security data sources in parallel, then uses Claude to reason over the combined signal the way a human security researcher would — but in under three seconds, and at a fraction of the cost. It's multi-chain, pay-per-use ready via OKX Web3, and built to be listed and called directly from OKX.AI.
Our bet is simple: as more of the economy moves to agents acting autonomously on-chain, "did anyone check this first?" becomes a question every agent needs answered — automatically, every time, before the money moves. SecurityGuard is that check.
<p>Designed and built SecurityGuard Agent end-to-end as a LangGraph workflow: input validation → parallel data fetching → parallel security analysis → LLM reasoning → structured output formatting.</p><ul><li><p>Implemented the core FastAPI service (<code data-inline="true" spellcheck="false">app.py</code>) with a stable <code data-inline="true" spellcheck="false">/v1/analyze</code> contract, <code data-inline="true" spellcheck="false">/health</code>, and <code data-inline="true" spellcheck="false">/docs</code>, plus API-key auth and rate limiting.</p></li><li><p>Built the LangGraph agent (<code data-inline="true" spellcheck="false">agent.py</code>) with a heuristic fallback path so the product stays demoable even without LLM access.</p></li><li><p>Integrated multiple blockchain and security data sources: Web3.py/RPC for on-chain data, honeypot.is and GoPlus for token/address risk signals, explorer APIs for contract verification and tx history, plus custom bytecode heuristics (SELFDESTRUCT/DELEGATECALL detection) and unlimited-<code data-inline="true" spellcheck="false">approve</code> calldata detection.</p></li><li><p>Added OKX Web3 enrichment and a pay-per-use payment verification flow (<code data-inline="true" spellcheck="false">okx_tools.py</code>), designed to be Agent Trade Kit–compatible.</p></li><li><p>Wired up Claude Sonnet 5 as the reasoning layer to turn raw findings into a calibrated 0–100 risk score, Low/Medium/High/Critical rating, and Approve/Warn/Block recommendation with a human-readable explanation.</p></li><li><p>Built a Gradio demo UI (<code data-inline="true" spellcheck="false">demo.py</code>) with preset scenarios (safe USDT vs. unlimited-approve phishing) for fast, repeatable demoing.</p></li><li><p>Set up SQLite-backed audit logging, containerized the service (Dockerfile), and prepared Railway/Render deploy configs for one-click hosting.</p></li><li><p>Recorded a demo comparing a clean token check against a phishing-style transaction to show the scoring and Block logic working end-to-end.</p></li></ul>
<p>Not yet raised. We're self-funded through the hackathon and plan to pursue pre-seed funding afterward to expand chain coverage, security integrations, and move SecurityGuard toward production-grade infrastructure.</p>