roblox-growth-design
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is primarily designed to analyze external, untrusted game data provided by users to the agent.
- Ingestion points: In
SKILL.md(Quick Reference) andreferences/full.md(§1 Operating Model), the agent is instructed to ask for and analyze Creator Dashboard screenshots, analytics exports, session recordings, and player feedback. - Boundary markers: No specific boundary markers or instructions to ignore instructions embedded within external data are present.
- Capability inventory: The skill contains no executable code, subprocess calls, file-write operations, or network-exfiltration capabilities.
- Sanitization: The instructions do not prescribe specific sanitization or validation steps for the external content being processed.
Audit Metadata