volatility-modeling

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

• Third-party content exposure detected (high risk: 0.90). This skill's runtime scripts (scripts/estimate_volatility.py: fetch_live_data and scripts/vol_forecast.py: fetch_live_returns) call the public Birdeye API (https://public-api.birdeye.so/defi/ohlcv) to ingest external OHLCV data, and those live inputs are used to compute forecasts, regime classifications, and position-sizing/stop decisions — so untrusted third‑party content can materially influence agent behavior.