frontend-design
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development operations, specifically stating to "Run the build after adding novel classes" when using Tailwind CSS in JIT mode. This is a functional requirement for the described tech stack.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill actively reads untrusted project data to gain context.
- Ingestion points: The skill reads project-level files including
package.json,tailwind.config.*,globals.css, Blade layouts, and documentation such asBRAND_GUIDE.mdorDESIGN.md. - Boundary markers: The skill does not define specific delimiters or "ignore previous instructions" markers when ingesting this project-specific content.
- Capability inventory: Based on the instructions, the agent has the capability to read/write files and execute shell commands (e.g., build commands).
- Sanitization: There is no evidence of content validation or filtering for the external project files before they are processed by the agent.
Audit Metadata