The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage its environment and run data retrieval tools. Specifically, it uses source ../../.venv/bin/activate to enter a virtual environment and runs Python scripts located in a sibling directory (../findata-toolkit-cn/scripts/views_runner.py).
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to perform package installations using pip install -r ../findata-toolkit-cn/requirements.txt to prepare the execution environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external financial platforms (e.g., East Money, Xueqiu) and user-provided inputs like tables or screenshots.
Ingestion points: Data is pulled from external API views via the views_runner.py script and from user-supplied data as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested financial data.
Capability inventory: The skill possesses the ability to execute shell commands and Python scripts within the local environment.
Sanitization: There is no evidence of sanitization or validation performed on the external data before it is processed by the agent.
[CREDENTIALS_UNSAFE]: The documentation in references/data-queries.md mentions the requirement for a XUEQIU_TOKEN environment variable to access certain data views, indicating the handling of sensitive API credentials.

hot-rank-sentiment-monitor