new-unity-project

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified. Ingestion points: User-provided project name and description captured in Step 1 of SKILL.md. Boundary markers: No delimiters or instructions are used to distinguish user data from agent commands. Capability inventory: Uses Bash for CLI execution and Write for project files in SKILL.md. Sanitization: No explicit escaping or validation is specified for user strings before shell interpolation.
  • [COMMAND_EXECUTION]: The skill interacts with the Unity CLI to manage project lifecycle, authentication, and licensing. This includes secure practices such as passing tokens via stdin.
  • [EXTERNAL_DOWNLOADS]: Fetches Unity Editor binaries and platform-specific modules through official vendor channels as part of the project setup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:31 PM
Security Audit — agent-trust-hub — new-unity-project