architecture-aware-init
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts such as
architecture_researcher.py,template_customizer.py, andattune_arch_init.pylocated within theplugins/attune/scripts/directory. These scripts are used to automate the research, selection, and scaffolding phases of the workflow. - [EXTERNAL_DOWNLOADS]: Utilizes the
WebSearchtool to retrieve current architectural patterns and best practices from the internet. This information is synthesized into a brief to inform the decision-making process. - [PROMPT_INJECTION]: The skill processes external data obtained from web searches to generate architectural recommendations. This creates a surface for indirect prompt injection (Category 8), where maliciously crafted web content could attempt to influence the agent's output. However, the risk is assessed as low given the advisory nature of the task and the structured workflow.
Audit Metadata