The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to communicate with an external API at api.openclaw.ai to perform market regime analysis.
[COMMAND_EXECUTION]: The skill utilizes a custom CLI tool openclaw to execute financial analysis commands, which involves subprocess execution.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from external financial feeds and CSV files.
Ingestion points: Historical price data and market metrics are fetched from external APIs (Yahoo Finance, Alpha Vantage) or loaded from user-provided CSV files.
Boundary markers: The skill does not define specific delimiters or "ignore instructions" guards for the data being processed.
Capability inventory: The skill uses the requests Python library for network communication and executes the openclaw CLI tool.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content within the data feeds before processing.

market-regime