ui-ugui

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection due to its core functionality of reading and analyzing external project data.
  • Ingestion points: As described in the 'Scope' and 'Workflow' sections, the agent analyzes existing Canvas hierarchies and .prefab UI files.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded within the hierarchy (e.g., in GameObject names or Text component strings).
  • Capability inventory: The agent is empowered to generate C# code, modify the project hierarchy, and execute Unity Editor APIs based on its analysis.
  • Sanitization: There are no instructions to sanitize or validate the data read from the UI hierarchy before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references the import of TextMeshPro (TMP) essential resources using Unity APIs.
  • It correctly recommends using TMP_PackageResourceImporter.ImportResources() to avoid blocking the agent with interactive modal dialogs.
  • These resources are official components of the Unity ecosystem and are considered safe platform-level assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:55 PM
Security Audit — agent-trust-hub — ui-ugui