Skills
Navigate
skills/idocohen560/claude-unity-game-studio/gameobject-find/Gen Agent Trust Hub

gameobject-find

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 recommends the installation of the unity-mcp-cli package via npm (npm install -g unity-mcp-cli) or running it via npx to function.
  • [COMMAND_EXECUTION]: The skill interacts with the Unity environment by executing shell commands through the unity-mcp-cli utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted string data (GameObject paths and names) from the Unity project hierarchy, which could be manipulated to include malicious instructions.
  • Ingestion points: The path and name properties within the gameObjectRef object in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input parameters.
  • Capability inventory: Shell command execution via unity-mcp-cli as specified in the usage examples of SKILL.md.
  • Sanitization: No input validation or sanitization routines are identified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:31 PM