Qc Deep Feature Forensics

12-dimensional technical feature attribution engine — compares winner vs loser trade entry conditions using RSI, Bollinger, MACD, volume surge, gap, and more...

This skill appears coherent and implements what it claims, but before running: (1) install dependencies inside a virtualenv/container to limit pip risk; (2) review the orders CSV you supply (it will be read and used as the sole input) and ensure it contains only the data you intend to analyze; (3) be aware the script will write a yfinance_cache/ folder beside your orders CSV and output files (feature CSV and feature_diagnosis.md); (4) the script requires internet on first run to fetch Yahoo data — if you need offline runs, pre-populate the cache; (5) if you handle sensitive trading/account data, inspect the full script locally (the included Python file appears to log only basic status messages) and run in an isolated environment. Overall the behavior is proportionate to the stated purpose.

Type: OpenClaw Skill Name: qc-deep-feature-forensics Version: 1.0.0 The skill bundle is a legitimate financial analysis tool designed to perform technical feature attribution on trading records. The Python script (deep_forensics.py) reconstructs trades from a CSV, fetches historical market data via the yfinance library, and calculates standard technical indicators (RSI, MACD, Bollinger Bands) to compare winning and losing entries. There is no evidence of data exfiltration, malicious execution, or prompt injection; the network activity is limited to Yahoo Finance, and file operations are restricted to reading the input CSV and managing a local cache directory (yfinance_cache).