design
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@chenglou/pretextutility package via NPM to handle typography measurement. It also encourages the use of established UI libraries including Tailwind CSS, FlyonUI, and daisyUI. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for cloning website designs from external URLs, which creates an attack surface for indirect prompt injection if the target content contains malicious instructions.
- Ingestion points: HTML content and screenshots retrieved from user-provided URLs in the 'External Content And Scraping' section (SKILL.md).
- Boundary markers: Not present; the instructions do not require the use of delimiters or 'ignore' commands for the scraped external content.
- Capability inventory: The skill facilitates file creation, component generation, and package installation across the frontend stack.
- Sanitization: No specific validation or sanitization requirements are defined for the data processed during cloning operations.
Audit Metadata