@1892/starchild-design-pack

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional markdown files and Python scripts designed to serve as a design system reference and auditing tool.
  • [EXTERNAL_DOWNLOADS]: The skill references a guidelines file from a well-known service for web development resources. These downloads are for static content and do not escalate the risk profile.
  • [COMMAND_EXECUTION]: The provided Python scripts (core.py, search.py, design_system.py) perform local text-based searches using a BM25 algorithm against provided CSV datasets. They do not invoke shell sub-processes or perform dangerous system-level commands.
  • [PROMPT_INJECTION]: Instructions within the markdown files follow standard guidance practices and do not contain patterns intended to bypass agent safety protocols or disregard system instructions.
  • [DATA_EXFILTRATION]: Analysis of the source code and datasets shows no attempts to access sensitive files (such as credentials or environment variables) or transmit data to external network locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 12:46 PM