apple-hig-expert

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive analysis of the skill's instructions, metadata, and scripts found no evidence of malicious behavior, data exfiltration, or security bypass attempts.- [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/hig_checker.py) to automate contrast and layout audits. The script employs standard libraries (json, math, argparse) to perform safe mathematical calculations for design compliance without network or system-level risks.- [PROMPT_INJECTION]: The skill is designed to ingest local context files such as product-context.md and ios-design-context.md to provide tailored advice. While it lacks explicit boundary markers or sanitization for these inputs, the risk is mitigated by the skill's limited capabilities, which are restricted to design consultation and localized tool usage.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 06:51 PM