weapp-tailwindcss-setup
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill reads and interprets external project data (e.g.,
package.json, Tailwind CSS configuration, and framework configs) to generate its output. This behavior creates a surface for indirect prompt injection attacks.\n - Ingestion points: The skill workflow reads the project's
package.json, Tailwind CSS entry points, and framework configuration files as specified inSKILL.mdandreferences/framework-matrix.md.\n - Boundary markers: The skill lacks explicit instructions or delimiters to isolate the untrusted project data from the agent's internal logic, making it susceptible to embedded instructions.\n
- Capability inventory: The skill generates setup commands (
pnpm add,pnpm exec) and technical configuration files (vite.config.ts, etc.) based on the input data.\n - Sanitization: No verification or sanitization of the content within the ingested project files is performed before processing.
Audit Metadata