specialist-game-development-level-designer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill interpolates user-provided text directly into a sub-agent prompt template, which is a common pattern for multi-agent workflows.
- Ingestion points: User input is interpolated via the
{the user's question}variable inSKILL.md. - Boundary markers: No explicit delimiters (like XML tags or quotes) are used to separate the user's question from the sub-agent's system instructions.
- Capability inventory: The skill is limited to spawning a sub-agent using the
Agenttool to process the user's request. - Sanitization: There is no evidence of input validation or escaping for the interpolated content.
Audit Metadata