architect
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured, multi-phase workflow for software architecture and planning, utilizing internal behavioral constraints and manual gates to ensure user oversight.
- [COMMAND_EXECUTION]: The skill uses research tools to scan project directories and read files to generate context maps. These operations are restricted to the local project environment and do not include arbitrary command execution or shell access.
- [DATA_EXFILTRATION]: No network operations or external data transfer patterns were detected.
- [PROMPT_INJECTION]: While the skill processes user input and reads repository files, it uses strict artifact templates and phased boundaries that prevent these inputs from overriding the agent's core planning instructions.
Audit Metadata