unity-run

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes shell commands to run the Unity editor and a local discovery script. This behavior is consistent with its stated purpose of automating Unity development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project paths and command-line flags provided by users or other skills to build shell commands. Ingestion points: project-root and caller-flags. Boundary markers: none. Capability inventory: subprocess execution of Unity. Sanitization: none mentioned in instructions. This represents a standard surface for indirect injection in automation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 09:36 PM
Security Audit — agent-trust-hub — unity-run