unity-llm-integration
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing user-controlled text directly into LLM dialogue calls (e.g.,
character.Chat(playerInput)). This architecture presents a potential surface for indirect prompt injection where untrusted input could attempt to manipulate the AI NPC's behavior. - Ingestion points: Found in
references/patterns.mdwithin theLLMManager,AsyncDialogueManager, andStreamingDialoguecode snippets. - Boundary markers: The provided code examples do not explicitly use delimiters or instructions to ignore embedded commands in player input.
- Capability inventory: The skill's functionality is limited to text generation and dialogue display; no high-risk capabilities such as file system writes, shell access, or external network exfiltration are present in the scripts.
- Sanitization: The examples demonstrate direct interpolation of input strings without additional sanitization or validation logic.
Audit Metadata