The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interacts with a remote API at https://mcp.fxmacrodata.com/mcp to fetch financial and macroeconomic data. This is the core functionality of the skill and is directed to a specific service domain (fxmacrodata.com) associated with the tool's purpose.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface through macroeconomic data retrieved from the external API.
Ingestion points: Data results from tools like indicator_query and latest_announcements in SKILL.md are loaded into the agent's context.
Boundary markers: None explicitly defined in the provided instruction file.
Capability inventory: The skill does not possess high-risk capabilities such as arbitrary shell command execution, local file system writes, or privilege escalation tools.
Sanitization: Not explicitly mentioned, but the risk is minimized by the specialized and structured nature of the returned financial data (numerical and statistical macro data).
[SAFE]: The documentation provides instructions for using API keys via environment variables (e.g., ${FXMACRODATA_API_KEY}) and HTTP headers. This avoids hardcoded secrets and follows standard secure configuration practices for secret management.

fxmacrodata