msw-avatar
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate guidance and code templates for game development tasks within the MSW ecosystem, specifically targeting CostumeManagerComponent and animation state mapping.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with external workspace files (.map, .model), which represents a potential ingestion surface for untrusted data.
- Ingestion points: Target project files including DefaultPlayer.model and map-specific files described in the target targeting table.
- Boundary markers: The skill does not define specific delimiters or instructions for processing untrusted content within these files.
- Capability inventory: Includes project file modification and invocation of platform tools like the msw-maker-mcp refresh tool.
- Sanitization: The skill provides strict guidance on looking up valid Resource Unique IDs (RUIDs) via the msw-search utility to prevent malformed or fabricated inputs.
Audit Metadata