skills/raddue/crucible/mock-to-unity/Gen Agent Trust Hub

mock-to-unity

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (HTML, images, text) during the mockup phase, presenting a risk of indirect prompt injection.
  • Ingestion points: Reads HTML files, screenshots, and text descriptions in Step 1 of SKILL.md.
  • Boundary markers: Employs a structured 'Translation Map' (Step 2) and a mandatory 'User Checkpoint' (Step 3) to verify mappings before implementation.
  • Capability inventory: Writes C# controllers and USS stylesheets to the Assets/ directory; updates a local reference file at ~/.claude/skills/mockup-builder/references/theme-variables.md.
  • Sanitization: The workflow requires manual verification of element hierarchies and property mappings against the source mockup.
  • [DATA_EXPOSURE]: The skill accesses a local reference file at ~/.claude/skills/mockup-builder/references/theme-variables.md to catalog and update theme variables. This is a localized reference used for maintaining consistency within the project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 10:34 PM