epa-ghgrp-subpartw

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is designed to fetch public regulatory data from the US Environmental Protection Agency (EPA).
  • Network operations: The skill uses curl to retrieve JSON data from the enviro.epa.gov domain, which is a well-known government service. These operations are limited to data retrieval (GET requests).
  • Data processing: The skill utilizes jq for parsing and aggregating structured data. No dynamic code execution or unsafe script generation patterns were identified.
  • Credentials: No API keys, tokens, or other sensitive credentials are required or used.
  • [NO_CODE]: The skill consists solely of markdown instructions and documentation, without any included scripts, executables, or binary files.
  • [PROMPT_INJECTION]: The skill processes data from an external source (EPA API), representing a surface for indirect prompt injection. Ingestion points: Data is retrieved from the enviro.epa.gov API endpoint. Boundary markers: The skill does not define specific delimiters for external content in its output format. Capability inventory: Capabilities are restricted to read-only network access via curl and data manipulation via jq. Sanitization: While no explicit text sanitization is performed on API fields like facility names, the trusted nature of the government source and the limited capability set mitigate this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 06:31 PM