skills/naimsolong/ai-software-agency/specialist-game-development-roblox-studio-roblox-avatar-creator/Gen Agent Trust Hub
specialist-game-development-roblox-studio-roblox-avatar-creator
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and metadata are consistent with its stated purpose of assisting in Roblox avatar creation. No malicious command execution, privilege escalation, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill uses a template that interpolates user input into a subagent's instructions, which is a standard pattern for multi-agent systems.
- Ingestion points: Untrusted user input enters the agent context via the
{the user's question}variable inSKILL.md. - Boundary markers: The user input is placed at the end of the subagent prompt; however, explicit delimiters or 'ignore' warnings for the interpolated string are absent.
- Capability inventory: The skill is restricted to spawning a subagent and providing instructional guidance; no file system writes or network operations are present in this skill.
- Sanitization: No explicit sanitization or filtering of the user variable is performed before interpolation.
Audit Metadata