frontend-design
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on high-quality frontend engineering and explicitly instructs the agent to respect brand constraints and check licensing before downloading assets. It prioritizes accessibility and performance.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external design systems and content to generate functional code, which presents a standard functional attack surface.
- Ingestion points: The "Inputs and worked example" section (SKILL.md) specifies that the skill collects existing design systems, content, and framework constraints.
- Boundary markers: The skill does not provide specific instructions to use delimiters or boundary markers when processing these external inputs.
- Capability inventory: The skill generates functional HTML, CSS, and JavaScript (SKILL.md, Section 5).
- Sanitization: The instructions do not define specific validation or sanitization protocols for the ingested design data.
Audit Metadata