building-3d-objects
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user data to generate and execute code in the Roblox environment.
- Ingestion points: User requests for object creation (e.g., "build me a ___", "create a ___") defined in
SKILL.mdare the primary source of untrusted data. - Boundary markers: There are no instructions for the agent to use delimiters or specific safety framing when incorporating user requirements into the generated Lua code.
- Capability inventory: The skill uses
mcp__roblox__run_code, which allows for arbitrary Lua code execution within the connected Roblox Studio instance. - Sanitization: The instructions do not define any validation or sanitization logic for user-provided structural details or descriptions before they are used to build executable code chunks.
Audit Metadata