design-an-interface
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for interface design exploration following established software design principles. It facilitates brainstorming through sub-agent delegation and records results in local project files.
- [DATA_EXPOSURE]: The skill writes architectural decisions to the project's local directory (specifically
.gsd/DECISIONS.mdandS##-CONTEXT.md). This is standard development workflow behavior and does not involve accessing sensitive system credentials, private keys, or environment variables. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requirements to generate design designs. While this represents a surface for indirect prompt injection where malicious input could attempt to influence sub-agent behavior, the skill's capabilities are limited to generating documentation and interface signatures, with no direct execution of the generated designs or network exfiltration patterns detected.
Audit Metadata