roblox-studio-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard workflow for Roblox development without introducing malicious code, persistence mechanisms, or unauthorized data access.- [PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters or override agent constraints.- [DATA_EXFILTRATION]: No hardcoded credentials or commands that exfiltrate sensitive local data.- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data (third-party assets), representing a potential attack surface. However, it incorporates specific security guidelines to mitigate this risk.
- Ingestion points: Third-party Creator Store or inventory assets via
insert_asset(SKILL.md). - Boundary markers: Explicitly instructs the agent to run
roblox-creator-store-security-auditafter importing third-party assets. - Capability inventory: Includes capabilities for code execution (
execute_luau), file modification (multi_edit), and simulated user input. - Sanitization: Relies on the external audit tool and instruction-based validation (e.g., reading scripts before editing).
Audit Metadata