ue-packaging-and-deployment
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process Unreal Engine project data (assets, maps, and configurations) and execute system-level build tools such as RunUAT.bat and UnrealEditor-cmd.exe. This creates a surface for indirect prompt injection if malicious instructions are present in the project data.
- Ingestion points: Unreal Engine project files (.uproject), assets (.uasset), and configuration files (.ini) as described in SKILL.md and referenced documentation.
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in the ingested project data.
- Capability inventory: Execution of shell scripts and build tools (RunUAT.bat, UnrealPak, UnrealEditor-cmd.exe) for compiling, cooking, and packaging project content.
- Sanitization: The skill does not prescribe methods for sanitizing or validating external project content before processing.
Audit Metadata