ue-ai-navigation
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides C++ code examples and architectural guidance for Unreal Engine AI development. Analysis of the provided instructions and reference files revealed no evidence of malicious intent, data exfiltration, or unauthorized command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read project-specific context from
.agents/ue-project-context.md. While this represents a data ingestion point where untrusted instructions could theoretically be placed, the skill's primary function is to generate local C++ code snippets based on verified engine APIs. It does not provide the agent with capabilities to execute shell commands, perform network operations, or write to the file system based on that context, rendering the attack surface negligible.
Audit Metadata