skills/bigdra50/unity-cli/unity-build/Gen Agent Trust Hub

unity-build

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a binary named u with various subcommands (build settings, build scenes, build run, api call). While these are specific to Unity development, they represent the primary interface for the agent to interact with the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data (scene lists and build configurations) to generate reports. There is a theoretical surface for indirect injection if a malicious project contains specially crafted scene names or metadata intended to influence the agent's output.
  • Ingestion points: Local Unity project data via the u CLI (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Subprocess execution of the u binary (SKILL.md).
  • Sanitization: Not explicitly defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 12:24 PM