building-maps

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows best practices for AI agent instructions, including clear scope boundaries and mandatory user clarification steps for ambiguous requests.
  • [COMMAND_EXECUTION]: Uses the mcp__roblox__run_code tool to execute Lua within a Roblox Studio environment. The provided code snippets are benign and focus on workspace manipulation (creating folders, parts, and verifying properties).
  • [PROMPT_INJECTION]: Includes defensive measures against vague or malicious prompts by requiring a structured <thinking> block and a checklist evaluation before execution.
  • [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were found. Analysis shows the code exclusively interacts with the Roblox Engine API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:12 AM