frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): The skill is composed entirely of natural language instructions and design guidelines. No scripts, commands, or data access patterns were found.
- PROMPT_INJECTION (LOW): The skill uses directive language such as 'CRITICAL' and 'IMPORTANT' to emphasize design principles like typography and motion. These do not constitute malicious injection as they do not attempt to bypass safety filters or override the agent's core identity.
- DATA_EXFILTRATION (SAFE): No network requests, file reads, or credential handling patterns are present.
- INDIRECT_PROMPT_INJECTION (INFO): The skill processes user-provided frontend requirements to generate code. While this is an ingestion point, it is the intended purpose of the skill and does not involve processing untrusted external data sources like URLs or third-party APIs by default.
Audit Metadata