subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes a secure orchestration design that separates the implementer from the reviewer, reducing the risk of autonomous errors or unreviewed code changes.
- [SAFE]: Instructions within the reviewer templates use emphatic language to enforce skepticism and independent verification of code, which is a benign and defensive design pattern.
- [SAFE]: The skill does not perform unauthorized network operations, access sensitive credentials, or attempt to persist across sessions.
- [SAFE]: The injection of task text into subagent prompts represents a standard operational surface area for development tools and is managed through structured review cycles.
Audit Metadata