unity-so-prefab-manager
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation describes the use of Unity-specific tools (mcp_unityMCP_manage_scriptable_object, mcp_unityMCP_refresh_unity) and generic file manipulation utilities (write_to_file, replace_file_content, grep_search) to perform batch updates and audits on Unity assets.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-level files that could potentially contain malicious instructions intended to influence the agent's behavior during management tasks.
- Ingestion points: The agent reads and parses .asset, .prefab, and .meta files within the Unity Assets directory, specifically during 'Surgical YAML' deep audits.
- Capability inventory: The agent has the ability to write to the file system, perform project-wide search-and-replace operations, and trigger Unity asset database refreshes.
- Boundary markers: There are no explicit instructions for the agent to treat content from project assets as untrusted or to use specific delimiters when processing these files.
- Sanitization: The skill does not prescribe any validation or sanitization routines for the content ingested from Unity assets before it is processed or used in subsequent steps.
Audit Metadata