software-engineer
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a well-structured set of engineering instructions focusing on best practices, maintainability, and security.
- [SAFE]: It implements a robust staged workflow (Stages 0-7) that requires explicit human approval at critical checkpoints (Stage 3 Plan and Stage 5 Implementation), which effectively mitigates risks associated with autonomous or unintended actions.
- [SAFE]: No evidence of data exfiltration, credential harvesting, or unauthorized network operations was found. The skill specifically instructs the agent to avoid committing secrets and to redact PII from logs.
- [SAFE]: The skill includes high-quality security references (e.g., references/nextjs.md, references/tanstack-start.md) that teach the agent how to implement secure data boundaries and protect against vulnerabilities like IDOR and CSRF.
Audit Metadata