The Agent Skills Directory

[SAFE]: The skill provides extensive design documentation and instructions for using established frontend frameworks. No malicious code, hardcoded credentials, or unauthorized network operations were identified.
[PROMPT_INJECTION]: Heuristic detections of actions concealment were reviewed and confirmed as false positives.
The references to "concealment" in reference/marketing-copywriting.md and reference/interface-honesty.md appear in the context of advising designers to avoid using "dark patterns" and deceptive interface practices.
[EXTERNAL_DOWNLOADS]: The skill references the installation of standard, legitimate frontend packages from established registries and official documentation.
Packages include sonner, vaul, and motion-v, which are standard in the referenced ecosystems.
Documentation links point to official domains such as nextjs.org and react.dev.
[COMMAND_EXECUTION]: The skill guides the use of official CLI tools for project setup and maintenance.
Includes usage of the shadcn/ui CLI and official Next.js codemods for project configuration.
[DATA_EXFILTRATION]: No patterns of unauthorized data collection or exfiltration were found. The skill includes explicit instructions for handling secrets in .env files, which is a standard security best practice.

frontend-design