map-systems
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a collaborative protocol, explicitly requesting user approval via
AskUserQuestionbefore performing any file writes or significant task transitions. - [SAFE]: Tool usage is restricted to standard file operations (Read, Write, Edit, Glob, Grep) and agent communication (AskUserQuestion, Task). No network or high-privilege system tools are enabled.
- [SAFE]: The use of the
Tasktool to spawn specialist agents (technical-director, producer) is a controlled orchestration pattern guided by local documentation. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from game concept documents. While this presents a theoretical attack surface, the risk is mitigated by the structured nature of the workflow and the requirement for manual user approval at each phase.
Audit Metadata