apply-aesthetic

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (design_systems.py, contrast.py) located in the .claude/skills/_ux-ui-shared/scripts/ directory to manage design systems and perform accessibility audits.
  • [EXTERNAL_DOWNLOADS]: The skill invokes npx shadcn@latest add to integrate UI primitives, which involves fetching components from the official shadcn registry using a well-known development utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads design specifications and token data from local project files, creating a potential surface for indirect instructions. Ingestion points: .claude/skills/_ux-ui-shared/taste/design-taste.md, .claude/skills/_ux-ui-shared/taste/aesthetic-systems.md, and .claude/skills/_ux-ui-shared/tokens/*.json. Boundary markers: Absent; no specific delimiters are defined in the instructions. Capability inventory: Defined in SKILL.md (Python script execution and npx tool usage). Sanitization: Absent; the skill relies on the integrity of the provided design system files.
  • [DYNAMIC_EXECUTION]: The skill utilizes Python to execute locally stored scripts with static paths, which is a standard method for modularizing skill functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 11:27 AM