type-get-json-schema
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation suggests the installation of the
unity-mcp-clipackage from the npm registry to enable its core functionality. - [COMMAND_EXECUTION]: The skill instructs the agent on how to execute shell commands using the
unity-mcp-clitool, passing user-provided JSON data to the command line. - [INDIRECT_PROMPT_INJECTION]: The skill processes the
typeNameinput to perform reflection operations, creating a potential attack surface where malicious type names or embedded instructions could be processed by the underlying tool. - Ingestion points: The
typeNameparameter within the tool's input schema. - Boundary markers: None are present in the documentation to delimit the input or instruct the agent to ignore embedded commands.
- Capability inventory: The skill utilizes the
unity-mcp-clifor executing code logic and performing reflection on C# assemblies. - Sanitization: There are no documented sanitization or validation steps for the external input before it is passed to the CLI tool.
Audit Metadata