board-game-quiz-maker
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an instructional template for an AI agent to generate educational content. It does not include executable code, external network requests, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided materials (question banks, lesson plans) to create interactive games. While this presents a theoretical attack surface for indirect prompt injection, it is the primary intended function of the skill and the risk is mitigated by the standalone, client-side nature of the generated outputs.
- Ingestion points: User-provided educational text and question sets via conversational input.
- Boundary markers: The skill instructs the agent to produce structured outputs (HTML/PDF), providing implicit structural boundaries.
- Capability inventory: File system writes to create .html, .pdf, and .md files in the local session directory.
- Sanitization: Relies on the AI model's standard safety guidelines for code generation.
Audit Metadata