design-an-interface
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows software design best practices (specifically the 'Design It Twice' principle from 'A Philosophy of Software Design') and contains no malicious instructions, obfuscation, or data exfiltration patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided module descriptions and requirements which are interpolated into prompts for sub-agents. While this is a potential attack surface for indirect prompt injection, it is standard for delegation tasks and the skill does not possess high-risk capabilities that could be exploited through this vector.
- [COMMAND_EXECUTION]: No unauthorized or dangerous shell commands or system-level operations were detected. The use of the
Tasktool for spawning sub-agents is a standard platform capability.
Audit Metadata