tailwind-modern
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it directs the agent to process untrusted data from the local environment.\n
- Ingestion points: The agent is instructed to read project files including
package.json,nuxt.config.*,vite.config.*, and various CSS entrypoints (referenced inSKILL.mdandreferences/framework-recipes.md).\n - Boundary markers: There are no explicit boundary markers or instructions to treat data within these files as untrusted or to ignore instructions embedded therein.\n
- Capability inventory: The agent has the capability to modify these configuration files and generate framework-specific setup code based on the content it reads.\n
- Sanitization: The skill lacks explicit sanitization or validation steps for the content extracted from the local project files.\n- [SAFE]: All external tools and packages mentioned, such as
@tailwindcss/vite,@tailwindcss/cli, andnuxi, are official utilities from well-known and trusted technology providers.\n- [SAFE]: The use ofnpxto execute these official tools is a standard and expected workflow for the described migration and setup tasks.
Audit Metadata