subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust implementation and review workflow with an emphasis on code quality and security through subagent delegation.
- [SAFE]: Includes explicit instructions to prevent credential leakage, such as checking for masked authorization syntax and auditing Git identities before pushing code.
- [SAFE]: Implements a two-stage review process (spec compliance and code quality) which serves as a defensive layer against errors, security vulnerabilities, and scope creep.
- [SAFE]: Recommends a 'preflight' audit of plans to identify contradictions or unsafe claims before any production code begins, reducing the risk of indirect prompt injection from malformed plans.
Audit Metadata