fancy-ui-craft

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/_skill_cli.py implements a run_command helper using subprocess.run. This function uses list-based arguments and does not enable shell execution, following best practices for environment interaction within agent skills.
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of standard and well-known NPM packages for UI development, including @vueuse/core, @tresjs/core, three, and @lottiefiles/dotlottie-vue. These are recognized as well-known dependencies for their stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests and processes UI code, it includes extensive design anti-patterns and stylistic constraints in context/ANTI_PATTERNS.md and context/PROSE_ANTI_SLOP.md which act as boundary markers and sanitization guidelines for the agent's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 05:10 AM