design-context

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs standard configuration management tasks by reading project files (e.g., tailwind.config.js, CSS variables) and writing to a local context file (.agents/design-context.md). These operations are aligned with its primary purpose and follow best practices for state persistence.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files to extract design tokens. This behavior is inherent to its primary purpose and uses targeted extraction logic.\n
  • Ingestion points: Reads from tailwind.config.js, globals.css, package.json, manifest.json, and components in the codebase.\n
  • Boundary markers: Absent; the skill relies on the structure of the target files.\n
  • Capability inventory: Performs file system read/write operations for context storage and retrieval.\n
  • Sanitization: Absent; the skill assumes the project files are trusted sources for design tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 06:34 AM