assets-find-built-in
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation suggests the global installation of
unity-mcp-clivia the NPM registry, introducing an external dependency from a source not explicitly listed as a trusted organization. - [COMMAND_EXECUTION]: The skill operates by executing shell commands using the
unity-mcp-cliutility, which runs external code on the host machine to interact with the Unity Editor. - [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary string data through its input parameters, which are then passed to a command-line interface, creating a vulnerability surface for data poisoning or indirect instructions.
- Ingestion points: The
nameandtypeinput parameters defined inSKILL.mdare used to receive user-controlled content. - Boundary markers: The skill does not define specific delimiters or warnings to isolate the input data from the command structure.
- Capability inventory: The skill relies on shell execution of the
unity-mcp-clitool (SKILL.md). - Sanitization: There is no documented mechanism for validating or escaping the provided string inputs before they are utilized by the command-line tool.
Audit Metadata