level-designer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified in the skill instructions or the execution script. The instructions are professional and strictly limited to game design concepts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user tasks through command-line arguments or stdin. Although no explicit boundary markers or sanitization steps are defined in the prompt to separate user input from the agent's core instructions, the skill's primary function is text-based documentation, which poses a negligible risk in this context.
- Ingestion points: User-provided tasks ingested via
scripts/run.sh. - Boundary markers: Not present in the current instructions.
- Capability inventory: The skill is designed for documentation and design specification (markdown output); no dangerous system-level or network capabilities are requested or used within the skill logic.
- Sanitization: Not specified in the current instructions.
Audit Metadata