The Agent Skills Directory

[COMMAND_EXECUTION]: The documentation in SKILL.md instructs the user to set up a recurring task using the openclaw cron command. This creates a persistence mechanism that executes the monitoring scripts every 5 minutes to report price alerts back to the agent.
[EXTERNAL_DOWNLOADS]: The scripts stocks_monitor.py, futu_stocks_monitor.py, and stocks_rebalance_monitor.py perform network requests to retrieve market data from Yahoo Finance and Futu OpenD endpoints. These operations are used for fetching real-time price information and do not download executable code.
[CREDENTIALS_UNSAFE]: The futu_stocks_monitor.py script is designed to read an unlock_password from a local JSON configuration file (futu_stocks_config.json). This facilitates the management of sensitive authentication data required to unlock the Futu trading API for market snapshots.
[PROMPT_INJECTION]: The skill processes data from external financial APIs, which represents a surface for indirect prompt injection if the API content were maliciously manipulated.
Ingestion points: Market data is ingested via urllib.request in stocks_monitor.py and the futu SDK in futu_stocks_monitor.py.
Boundary markers: No specific delimiters or safety warnings are included in the script outputs processed by the agent.
Capability inventory: The skill generates text alerts; it does not involve subprocess execution or dynamic code evaluation based on the retrieved data.
Sanitization: Scripts utilize JSON parsing and explicitly cast price values to floats, which provides sanitization for the primary data fields.

stock-monitor