The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which serves as a potential attack surface for indirect prompt injection.
Ingestion points: The skill ingests user-provided materials such as transcripts, platform notes, and event lists (SKILL.md), as well as JSON responses from external financial APIs (references/providers/fmp.md, references/providers/tradingeconomics.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill's capabilities are limited to data retrieval, analysis, and text generation. No dangerous operations like file system writes or code execution are present.
Sanitization: No sanitization or validation of the ingested external content is described.
[EXTERNAL_DOWNLOADS]: The skill is designed to fetch economic event data from external services.
Evidence: The skill references and provides instructions for fetching data from FinancialModelingPrep (financialmodelingprep.com) and TradingEconomics (api.tradingeconomics.com), which are well-known financial data providers.
[COMMAND_EXECUTION]: The skill provides specific command-line instructions for the agent to execute.
Evidence: Templates for curl commands are provided in references/providers/fmp.md and references/providers/tradingeconomics.md to retrieve JSON data from remote APIs.

macro-event-analysis