deterministic-design

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or persistence mechanisms were detected in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references external sub-skills and a layout audit script (layout-audit.js) hosted on a public GitHub repository (github.com/connerkward/deterministic-design-skill). These are identified as vendor-owned resources and are used for extending functionality.
  • [COMMAND_EXECUTION]: The instructions describe a workflow involving the execution of a JavaScript tool to compute layout metrics like centroid and optical-center balance. This is a functional part of the design audit process.
  • [SAFE]: The skill processes rendered UI and screenshots, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Rendered UI or screenshots (processed via vision tools).
  • Boundary markers: Not specified.
  • Capability inventory: Shell script execution (layout-audit.js) and vision-based heuristic judging.
  • Sanitization: No explicit sanitization of UI content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 11:37 AM
Security Audit — agent-trust-hub — deterministic-design