design-taste-frontend
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative language such as 'BANNED', 'CRITICAL', and 'MANDATORY' to enforce specific design aesthetics and coding standards. These instructions aim to prevent common AI design clichés and stylistic inconsistencies rather than bypassing safety filters or extracting system prompts.
- [COMMAND_EXECUTION]: The agent is instructed to check the local
package.jsonfor missing dependencies and suggestnpm installcommands to the user. This is a standard developer-assistant pattern and does not involve the agent executing commands on the host system without user oversight. - [EXTERNAL_DOWNLOADS]: References to
picsum.photosare included for generating placeholder image URLs. This is a well-known and reputable service commonly used in web development for prototyping, and its use here is documented neutrally as part of the design guidelines.
Audit Metadata