The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs HTTP GET requests to retrieve financial datasets from the official U.S. Treasury API (api.fiscaldata.treasury.gov). This is a well-known government service and is the primary purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints, creating a potential attack surface for indirect prompt injection.
Ingestion points: The skill uses requests.get to fetch data from various U.S. Treasury endpoints as described in SKILL.md and references/examples.md.
Boundary markers: No explicit prompt delimiters or instructions are provided to the agent to treat the fetched data as untrusted content.
Capability inventory: The skill is configured with Bash, Read, Write, and Edit tools, allowing it to execute commands and modify files based on processed data.
Sanitization: The provided code examples use pandas and decimal.Decimal to cast input strings to specific numeric or date types, which provides a layer of validation against non-numeric injection payloads in financial fields.

usfiscaldata