design-taste-frontend
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-provided design briefs and vibe descriptions to drive the generation of frontend code and layout structures. This creates a surface where malicious instructions embedded in a brief could potentially influence the agent's output.
- Ingestion points: User briefs, visual vibe descriptions, and reference signals defined in SKILL.md.
- Boundary markers: The skill utilizes a mandatory "Design Read" one-line summary before code generation, but does not employ strict delimiters to isolate untrusted user inputs.
- Capability inventory: The skill generates executable React/Next.js code, uses animation libraries like GSAP and Motion, and provides instructions for package installation.
- Sanitization: No validation or sanitization logic is defined for the content of the user-provided briefs.
- [COMMAND_EXECUTION]: The skill provides explicit instructions and commands for installing various third-party Node.js packages and design systems, such as Fluent UI, Carbon, and Radix Themes (SKILL.md, Appendix A).
Audit Metadata