assets-prefab-open

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The documentation references the installation of unity-mcp-cli via npm. This is a vendor-specific command-line tool (matching the author 'ivanmurzak') necessary for the skill's intended operation within the Unity ecosystem.
  • [COMMAND_EXECUTION]: The skill facilitates interaction with the Unity Editor by executing shell commands through the unity-mcp-cli utility. This is the primary mechanism for the tool's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which presents a theoretical attack surface.
  • Ingestion points: The gameObjectRef input parameter in SKILL.md, including path, name, and assetPath fields, which are populated from the active Unity project hierarchy.
  • Boundary markers: None explicitly defined in the input schema to separate data from instructions.
  • Capability inventory: The skill executes shell commands (unity-mcp-cli) and modifies the Unity Editor state (SKILL.md).
  • Sanitization: Input is constrained by a JSON schema, providing structural validation, though it does not explicitly filter for natural language instructions within the strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 12:15 PM