unity-project-bootstrap

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the unity-cli tool and the Unity Editor binary to automate project lifecycle tasks. It includes instructions to run local setup scripts (scripts/install.sh or scripts/install.ps1) to ensure the necessary binaries are available in the execution environment.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to configure the Unity project to interface with the OpenUPM registry and install the com.akiojin.unity-cli-bridge package. These are standard operations for Unity development and use well-known community infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection as it ingests and processes data from external files and terminal outputs.
  • Ingestion points: Project manifest files (Packages/manifest.json), version configuration (ProjectSettings/ProjectVersion.txt), and live terminal output captured from the Unity console via the read_console tool.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing of console logs.
  • Capability inventory: The skill possesses significant capabilities to modify the file system and execute project-related shell commands using Bash(unity-cli:*).
  • Sanitization: The instructions do not specify any sanitization or validation routines for the content ingested from logs or project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 12:02 AM