usfiscaldata

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the U.S. Treasury Fiscal Data API (e.g., api.fiscaldata.treasury.gov). This represents a potential indirect prompt injection surface if the external data source were to contain malicious instructions.
  • Ingestion points: Data is fetched via requests.get() calls in SKILL.md and references/examples.md.
  • Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded content in the API responses.
  • Capability inventory: The skill has access to Bash, Read, Write, and Edit tools as defined in SKILL.md.
  • Sanitization: Code examples demonstrate standard parsing of JSON and CSV data into DataFrames, which provides structural validation but not semantic sanitization against prompt injection.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install standard, well-known Python packages (requests, pandas) using standard package managers.
  • Downloads: Fetches financial data and documentation from official U.S. Treasury domains (api.fiscaldata.treasury.gov, fiscaldata.treasury.gov) and citation metadata from arXiv (arxiv.org).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:05 AM
Security Audit — agent-trust-hub — usfiscaldata