The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl commands in its reference documentation to retrieve JSON-formatted financial data from external API endpoints. These commands are intended for data acquisition only and do not involve piping output to shells or executing remote scripts.
[EXTERNAL_DOWNLOADS]: Fetches economic calendar information from financialmodelingprep.com and api.tradingeconomics.com. These are well-known financial data services, and the data retrieval is used to populate the analysis framework.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes data from external APIs.
Ingestion points: API responses from Financial Modeling Prep and Trading Economics as specified in references/providers/fmp.md and references/providers/tradingeconomics.md.
Boundary markers: The skill does not define explicit boundary markers or 'ignore previous instructions' directives for the data being interpolated into the prompt context.
Capability inventory: The agent primarily performs textual analysis and report generation based on the data; no high-risk capabilities like file system modification or subprocess execution were identified in the skill scripts.
Sanitization: The skill limits exposure by instructing the agent to extract specific JSON fields (e.g., date, event, impact), which restricts the volume of unprocessed third-party text entering the context.

macro-event-analysis