frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No malicious override or bypass instructions were detected. The use of markers like 'CRITICAL' and 'IMPORTANT' is contextually appropriate for emphasizing design principles rather than attempting to subvert agent safety protocols.- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local file paths or include hardcoded credentials. No network operations or non-whitelisted domains were identified.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute any external packages or scripts. It relies entirely on the model's internal knowledge to generate code.- [No Code] (SAFE): No executable code files (e.g., .py, .js, .sh) are included with the skill; it consists solely of markdown-based instructions for the AI agent.
Audit Metadata