map-design-language

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs read-only research on project structures (e.g., package.json) and source files to identify toolkits and styling tokens. This is consistent with its stated purpose of mapping design language.
  • [SAFE]: All writing operations are restricted to a specific file (meta/DESIGN.md) and require explicit user confirmation via an 'AskUserQuestion' prompt before execution.
  • [SAFE]: The skill uses sub-agents for parallel research tasks, which is a standard pattern for complex analysis. These sub-agents are restricted to read-only operations.
  • [SAFE]: No patterns associated with data exfiltration, credential harvesting, or unauthorized command execution were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:02 PM
Security Audit — agent-trust-hub — map-design-language