The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for activating a virtual environment and running Python scripts located in sibling directories outside the skill's root (e.g., ../../.venv/bin/activate and ../findata-toolkit-cn/scripts/views_runner.py).
[EXTERNAL_DOWNLOADS]: The skill triggers the installation of Python dependencies using pip install -r from a local requirements file (../findata-toolkit-cn/requirements.txt) that is external to the skill's own directory.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted market data from external financial tools (e.g., stock_board_industry_name_em) into analytical reports. * Ingestion points: Data queries defined in references/data-queries.md which fetch JSON from various market providers. * Boundary markers: None identified in the workflow or output templates. * Capability inventory: The skill has the capability to execute shell commands and run arbitrary Python scripts from the local filesystem. * Sanitization: No data validation or sanitization logic is specified for the content returned by the market data tools.

industry-chain-mapper