roblox-game-design
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions promote security best practices for game development, including explicit checks for server authority, data validation, and anti-exploit measures. The agent is also instructed to identify exploit cases and define server-side checks as part of the system design standard.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external content including project documentation and live place data from Roblox Studio, which represents a surface for indirect prompt injection.
- Ingestion points: Instructions require reading existing concept, design, roadmap, and implementation documents (SKILL.md), as well as inspecting live places via the Roblox Studio MCP tool.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided in the prompts to isolate untrusted external content.
- Capability inventory: The skill has access to the Roblox_Studio MCP tool and instructions to author and modify design documents.
- Sanitization: No explicit content validation or sanitization rules are defined for the ingested data.
Audit Metadata