skills/anian0/pick-skills/tech-design/Gen Agent Trust Hub

tech-design

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill incorporates strong operational boundaries, specifically a 'HARD-GATE' that forbids the agent from writing code or creating project structures, effectively mitigating risks associated with unauthorized file creation or code execution.
  • [SAFE]: File access and creation are restricted to specific, documented directories within a 'workplace' path, ensuring that the agent's actions remain within a predictable scope.
  • [SAFE]: The workflow enforces a 'Confirm-Before-Proceed' pattern at every step (requirements understanding, architecture, data model, API, and frontend), which ensures human oversight and prevents the agent from operating autonomously without validation.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or insecure dependency management was found in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:33 AM