subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured framework for delegating tasks to subagents. It consists of coordination instructions and prompt templates for implementation and review roles. No malicious logic or unauthorized operations were found in any of the components.- [COMMAND_EXECUTION]: The workflow describes subagents performing standard software development tasks such as writing code, running tests, and committing changes. These actions are within the intended scope of a development tool and follow a controlled process with mandatory review steps to ensure integrity.- [PROMPT_INJECTION]: The templates include specific instructions for subagents to follow (e.g., 'CRITICAL: Do Not Trust the Report'). These are benign meta-prompts used to increase the accuracy and thoroughness of the AI subagents by encouraging skepticism of previous task results, rather than attempts to bypass system security filters or safety guidelines.
Audit Metadata