frontend-design
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides architectural guidelines, design tokens, and aesthetic archetypes for creating frontend interfaces. Analysis of all provided files confirms the absence of malicious patterns, prompt injection attacks, or data exfiltration vectors.
- [NO_CODE]: This skill consists entirely of documentation and instructional markdown files. It does not ship with any executable scripts (Python, Node.js, or Shell), significantly reducing the potential attack surface.
- [EXTERNAL_DOWNLOADS]: Several archetype reference files (e.g.,
references/archetypes/art-deco.md,references/archetypes/editorial.md,references/archetypes/lo-fi.md) reference Google Fonts via@importor<link>tags. These are well-known, trusted services used for typography and do not pose a security risk. - [PROMPT_INJECTION]: While the skill defines a workflow for processing user-provided 'Design Briefs' (Category 8: Indirect Prompt Injection surface), it incorporates a mandatory 'Critic Self-Review' protocol in
references/critique-framework.mdto ensure output quality and coherence. The injection risk is inherent to the skill's purpose and is managed by the agent's internal constraints.
Audit Metadata