unreal-engine

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed as a developer assistant for Unreal Engine. It contains standard C++ and Blueprint patterns, architectural guidelines, and a robust set of static analysis rules (implemented via regex) to help users avoid common engine-specific pitfalls such as garbage collection crashes or networking errors. No evidence of prompt injection, data exfiltration, or unauthorized code execution was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review user-provided code (C++ and Blueprints) across files like references/validations.md and references/sharp_edges.md. While this establishes an ingestion point for untrusted data, the agent lacks capabilities for file writing, network requests, or shell execution, limiting the risk to purely advisory content. The instructions mandate grounding responses in the provided reference files, which acts as a boundary against user-supplied overrides.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 07:58 AM