Skills
Navigate
skills/unity-technologies/skills/new-unity-project/Gen Agent Trust Hub

new-unity-project

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes unity and git commands through the bash tool to handle authentication, project scaffolding, and source control operations.\n- [EXTERNAL_DOWNLOADS]: The skill initiates downloads of the Unity Editor and platform-specific modules from the vendor's official servers via the unity install command.\n- [INDIRECT_PROMPT_INJECTION]: The skill incorporates untrusted user data into command-line arguments.\n
  • Ingestion points: User-provided strings for project names and descriptions are collected using AskUserQuestion in SKILL.md.\n
  • Boundary markers: The instructions do not specify any delimiters or safety markers for the user-supplied input.\n
  • Capability inventory: The skill utilizes shell execution and file system write capabilities.\n
  • Sanitization: No validation or sanitization steps are defined for the user input prior to execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:25 PM
Security Audit — agent-trust-hub — new-unity-project