setup-tailwind-typescript
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of several well-known and trusted utility packages from the NPM registry, such as tailwindcss, postcss, clsx, and tailwind-merge. These are standard dependencies for modern web development.
- [COMMAND_EXECUTION]: The procedure includes the use of 'npx tailwindcss init', which is the official and standard command for generating Tailwind configuration files within a project directory.
- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by ingesting untrusted user data (Design system tokens and Tailwind plugins) and using them to modify project files.
- Ingestion points: Design system tokens (colors, spacing, fonts) and plugin lists defined in the 'Inputs' section of SKILL.md.
- Boundary markers: Absent; there are no specific instructions or delimiters provided to prevent the agent from interpreting embedded instructions within the token data.
- Capability inventory: The skill allows 'Bash' for package installation and 'Write'/'Edit' for modifying configuration and source files (tailwind.config.ts, globals.css, cn.ts).
- Sanitization: None; the skill does not suggest validation or escaping of the provided tokens before they are interpolated into the code templates.
Audit Metadata