RugPullRadar

Rug pulls drain billions of dollars from crypto buyers every year, and the warning signs are almost always sitting in public on-chain data before the collapse - concentrated ownership, un-renounced ownership, dangerous contract functions, serial-deployer wallets, unlocked liquidity - but they are scattered across a block explorer and unreadable to a non-technical buyer. RugPullRadar takes a token contract address on Ethereum, BNB Chain, Base or Arbitrum and reads that data through the free Etherscan V2 API. It scores five independent, individually-explained risk signals into a single 0-100 composite (LOW / MODERATE / HIGH RISK), shown as a five-axis radar whose shape communicates the risk profile at a glance. A language model - Qwen2.5-7B-Instruct served through vLLM on AMD Instinct (ROCm) - then writes the verdict in plain English and produces a concrete "verify-yourself" checklist. If the model is offline the app falls back to a deterministic template, so it never hard-fails. The scoring is transparent, deterministic math on CPU; the language reasoning - the part that genuinely needs a model - runs on AMD hardware. The whole app is a containerized FastAPI service with a single-page frontend and a JSON API. Built for the AMD Developer Hackathon: ACT II, Track 3 (Unicorn).