backtesting-bias-avoidance

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

• Third-party content exposure detected (low risk: 0.10). Runtime path scripts/run_backtest.py: load_prices() ingests only first-party inputs (synthetic generated series or yfinance price OHLC fetched via an explicit --source/--symbol), and the skill’s core workflow doesn’t read arbitrary outsider-authored free text unless the user explicitly provides it as parameters or via trusted price data.