frontend-design
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any malicious code, command execution, or data exfiltration attempts. It focuses entirely on providing guidance for typography, layout, and visual identity.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing user-provided design briefs and subject matter to generate UI designs, which creates a standard data ingestion surface for the agent.
- Ingestion points: User-supplied design briefs and client context referenced throughout
SKILL.md. - Boundary markers: None explicitly defined in the instructions for delimiting external content.
- Capability inventory: The skill instructs the agent to generate and write code based on the designed plan.
- Sanitization: The instructions do not provide specific guidance on sanitizing or validating the input brief or subject matter.
Audit Metadata