frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and focused on architectural reasoning for frontend design. It does not include any code, scripts, or tool invocations that interact with the host system or network.- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as UI briefs and brand constraints, creating a theoretical surface for indirect prompt injection.\n
- Ingestion points: Inputs defined in
SKILL.mdinclude UI briefs, current interfaces, and design context.\n - Boundary markers: The skill does not define specific delimiters or guardrails to differentiate between instructions and user-provided data.\n
- Capability inventory: There are no capabilities for subprocess execution, filesystem modification (other than artifact creation), or network access.\n
- Sanitization: No input sanitization or validation logic is present.\n
- Analysis: Although the skill ingests untrusted data, the absence of any functional tools or execution capabilities makes the risk of this surface negligible.
Audit Metadata