The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill utilizes several third-party Python libraries to interface with economic APIs. While these are well-known in the data science community, they are external dependencies.
Packages: fredapi, wbdata, pandas, bls, pandasdmx, yfinance.
[CREDENTIALS_UNSAFE] (SAFE): The skill follows security best practices by explicitly instructing users to use environment variables for API keys and includes logic to check for these variables before execution.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests data from external API endpoints, which represents a potential surface for indirect injection if an API were compromised.
Ingestion points: Network responses from FRED and World Bank APIs are loaded into Pandas DataFrames in the generated code within SKILL.md.
Boundary markers: Absent; data is processed directly as received from the providers.
Capability inventory: The code has the capability to write the resulting data to the local filesystem via to_csv().
Sanitization: No sanitization is performed on the incoming data before it is written to disk, which is standard for numeric data fetching utilities.

api-data-fetcher