skills/lynricsy/hyperskills/unity/Gen Agent Trust Hub

unity

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate technical documentation, best practices, and evaluation cases for Unity 6 development. All provided scripts and command examples are standard practices for the platform's CI/CD and development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process Unity project files, including source code (.cs), assembly definitions (.asmdef), and package manifests. This creates an attack surface for indirect prompt injection from within the project data it analyzes. However, the instructions focus on structural and performance-based analysis, reducing the risk of accidental obedience to embedded instructions.
  • Ingestion points: Project source code under Assets/, .asmdef files, Packages/manifest.json, and ProjectSettings/ProjectVersion.txt.
  • Boundary markers: None explicitly defined in the instructions for separating ingested file content.
  • Capability inventory: The skill describes the use of the Unity Editor CLI (Unity.exe / Unity) for batch-mode builds and test execution.
  • Sanitization: No specific sanitization or escaping mechanisms for ingested source code are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 03:14 PM
Security Audit — agent-trust-hub — unity