skills/kessriga/game-studio/ux-design/Gen Agent Trust Hub

ux-design

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the local project directory, reading from and writing to paths like 'design/ux/' and 'design/gdd/'. It does not attempt to access sensitive system files or credentials.
  • [SAFE]: All content creation follows a 'Question -> Options -> Decision -> Draft -> Approval -> Write' workflow. This human-in-the-loop requirement ensures that the agent cannot autonomously inject or modify files without the user's explicit consent for each specific section.
  • [SAFE]: The skill contains no network-enabled tools (like curl or wget) or obfuscated content. All logic is transparently defined in Markdown and standard shell-compatible instructions.
  • [SAFE]: Specialist agent routing via the Task tool is scoped to internal coordination between named roles (e.g., art-director, ui-programmer) and explicitly forbids these sub-agents from writing to files directly, maintaining a strictly controlled output process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:18 PM
Security Audit — agent-trust-hub — ux-design