The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial markets and company reports which could potentially be manipulated to include adversarial instructions intended to influence the agent's trading decisions.
Ingestion points: scripts/market_data.py, scripts/financial_data.py, and scripts/sector_data.py fetch data from the xtquant library which connects to the local MiniQMT client.
Boundary markers: The skill does not implement explicit boundary markers or instructions for the agent to ignore embedded commands in the fetched data.
Capability inventory: scripts/trade.py provides the ability to place orders, cancel orders, and query account assets.
Sanitization: The scripts return raw data in JSON format without specific sanitization for prompt injection patterns.
[EXTERNAL_DOWNLOADS]: The documentation provides links to download the xtquant library and historical datasets from the official vendor's domain (dict.thinktrader.net). These are legitimate and expected resources for the quantitative trading platform.
[COMMAND_EXECUTION]: The skill facilitates the execution of Python scripts (scripts/market_data.py, scripts/trade.py, etc.) that interact with the local MiniQMT quantitative trading terminal via the xtquant library.

miniqmt