clean-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No security issues detected. The skill defines a persona and rules for software architecture without including any functional code or scripts.
- PROMPT_INJECTION (SAFE): The content consists of legitimate architectural instructions and does not attempt to bypass agent safety filters or override system instructions.
- DATA_EXFILTRATION (SAFE): There are no references to sensitive file paths, environment variables, or unauthorized network communication.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not perform any remote downloads or execute external commands.
Audit Metadata