luau-roblox-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and audit external Luau scripts, creating a surface where untrusted data (the code being reviewed) enters the agent's context.
- Ingestion points: The skill instructions involve 'Reviewing, debugging, or optimizing Luau scripts', which requires reading user-provided or repository-sourced files.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the code comments or strings of the scripts being reviewed.
- Capability inventory: While the skill body focuses on the Roblox engine context, the AI agent using the skill typically has broader file system and execution capabilities that could be targeted by instructions hidden in the audited code.
- Sanitization: The instructions lack guidance on sanitizing script content or handling potentially malicious instructions within the audited code's comments or logic.
Audit Metadata