frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): Natural instructional language like 'CRITICAL' and 'IMPORTANT' is used exclusively to emphasize design choices. No patterns indicating safety bypass or system prompt extraction were detected.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations are present.
- [Unverifiable Dependencies] (SAFE): No package installations or remote script executions are defined. Mention of 'Motion library' is for framework context only.
- [Indirect Prompt Injection] (SAFE): The skill possesses a surface for indirect injection via user-provided requirements (Ingestion point: user requirements in SKILL.md; Boundary markers: absent; Capabilities: UI code generation only; Sanitization: absent). However, as it lacks dangerous capabilities like system command execution or network access, the surface is not exploitable in a malicious context.
Audit Metadata