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 detected. Phrases like 'CRITICAL' and 'IMPORTANT' are used legitimately to emphasize design principles and do not attempt to subvert agent safety boundaries.
- [Data Exposure & Exfiltration] (SAFE): The skill does not contain any commands to read sensitive files, access credentials, or transmit data to external servers.
- [Remote Code Execution] (SAFE): There are no patterns involving the download or execution of remote scripts. The skill focuses entirely on the generation of static frontend code (HTML/CSS/JS).
- [Indirect Prompt Injection] (LOW): The skill processes user-provided requirements to generate code. While it lacks explicit boundary markers for user input, its primary function is creative code generation rather than data processing, posing minimal risk to the agent's integrity.
Audit Metadata