The Agent Skills Directory

[SAFE]: The skill instructions were analyzed for all threat categories including prompt injection, data exfiltration, and obfuscation. No malicious patterns were found. The use of markers like 'CRITICAL' and 'IMPORTANT' is strictly instructional and related to design principles.
[NO_CODE]: This skill consists of a single markdown file containing design guidelines. It does not include scripts, binaries, or references to external code execution.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-provided frontend requirements to generate code. While this is an ingestion point for untrusted data, the skill does not possess sensitive capabilities such as file system writing or network access that could be exploited.

frontend-design