frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The persona-driven instructions are focused on aesthetic output and do not contain bypass or override patterns.
- Data Exposure & Exfiltration (SAFE): No sensitive data access or network exfiltration patterns were detected. The skill is limited to UI generation.
- Unverifiable Dependencies (SAFE): The skill recommends standard frameworks like Astro and Next.js and does not perform runtime remote code execution or package installation.
- Indirect Prompt Injection (SAFE): The skill has a surface for indirect prompt injection because it processes existing frontend code for restyling. However, the risk is negligible as the agent lacks dangerous capabilities like OS command execution or network access.
- Ingestion points: Existing frontend code files identified for restyling.
- Boundary markers: Absent in the current instruction set.
- Capability inventory: Limited to generating CSS, HTML, and component code.
- Sanitization: Not present.
Audit Metadata