The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute local shell and Python scripts for installation, testing, and data retrieval, including scripts/install.sh, scripts/em.py, scripts/test.sh, and model training scripts.
[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes news, reports, and stock data from external sources (Eastmoney and Sina), which could potentially contain adversarial instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested via the get_news_and_reports and get_market_news tools within the scripts/em.py script.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands were found in the provided documentation.
Capability inventory: The skill environment allows for local script execution and network requests to financial data providers.
Sanitization: The documentation does not describe any specific sanitization or filtering of the external text content before it enters the agent's context.

eastmoney-api