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

unreal

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a code analysis and implementation assistant for Unreal Engine source code (C++ and C# Build.cs files).
  • Ingestion points: The skill instructions and workflows in SKILL.md describe reading and analyzing user-provided .h, .cpp, and .Build.cs files.
  • Boundary markers: No explicit delimiters or boundary instructions are provided to isolate untrusted input code from the agent's instructions.
  • Capability inventory: The skill provides instructions for interacting with the file system and executing platform-specific build tools like RunUAT.bat and UnrealEditor-cmd.exe.
  • Sanitization: The skill does not mention sanitizing or escaping content from analyzed files before processing.
  • [EXTERNAL_DOWNLOADS]: SOURCES.yaml and NOTICE.md list several external GitHub repositories and official documentation sources used for technical verification and attribution. This includes references to the official Epic Games repository for editor automation tools, which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill provides template shell commands in SKILL.md and references/unreal-build.md for building, cooking, and running automation tests using the Unreal Automation Tool (RunUAT.bat) and the Unreal Editor command line. These are standard development workflows for the target platform.
  • [DYNAMIC_EXECUTION]: The documentation describes the use of Unreal Engine's 'Live Coding' and 'Automation Test' frameworks. These involve runtime patching and executing code within the engine environment, which are legitimate features being documented for developer use.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 03:14 PM
Security Audit — agent-trust-hub — unreal