crypto-token-screener

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow fetches outsider-authored free text/data from public APIs—DefiLlama fees/holder revenue and CoinGecko market/price history—via scripts/screen.py using urllib.request.urlopen() on https://api.llama.fi/... and https://api.coingecko.com/..., and then injects the resulting readable numeric fields into the agent’s LLM context when the agent summarizes/ranks them.