Agent skill · Audited from source

build-live-game

skill · unity-technologies/skillsNOASSERTION licenceAudited 20 Oct 2026 · source 088088af666d

★ 1,114pushed today
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 088088a
1,114repo stars · whole unity-technologies/skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 088088af666d and found no filesystem, network or shell access and no hard-coded secrets. What it does: Builds and operates live games with Unity Services. Use when the user asks about backend or live-ops features such as player accounts, cloud save, leaderboards, achievements, progression and battle passes, economies,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “build-live-game (unity-technologies/skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/unity-technologies/build-live-game

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low3 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS3
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (3)

INFOPrompt injectionprompt.authority_framing · references/apis.md:39
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
> or write UGS data with elevated privileges must use this package. There is no other
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.authority_framing · references/apis.md:65
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Used for backend tooling, editor extensions, Deployment Window integrations, and any operation that requires elevated privileges. **Editor-only** — guarded by `#if UNITY_EDITOR || ENABLE_RUNTIME_ADMIN
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.authority_framing · references/apis.md:191
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Elevated server client with admin-equivalent access to player data. Use when a dedicated server needs to read or modify any player's data with elevated privileges.
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 088088af666d · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherunity-technologies GitHub organizationOwner of the repository this skill is read from
  • Source folderunity-technologies/skills/skills/build-live-gameThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict088088af666dA new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Builds and operates live games with Unity Services. Use when the user asks about backend or live-ops features such as player accounts, cloud save, leaderboards, achievements, progression and battle passes, economies,…

---
name: build-live-game
description: Builds and operates live games with Unity Services. Use when the user asks about backend or live-ops features such as player accounts, cloud save, leaderboards, achievements, progression and battle passes, economies, cloud code, or remote config.
---

# Build a Live Game With Unity Gaming Services

## UGS Packages

| Package | Min Version | Purpose |
|---|---|---|
| `com.unity.services.core` | 1.16.0 | Initialization, dependency graph |
| `com.unity.services.authentication` | 3.6.1 | Player sign-in and identity |
| `com.unity.services.cloudcode` | 2.10.3 | Server-authoritative C# modules |
| `com.unity.services.cloudsave` | 3.4.0 | Per-player and shared key-value storage |
| `com.unity.remote-config` | 4.2.5 | Server-side game configuration |
| `com.unity.services.deployment` | 1.7.2 | Deploy cloud resources from Editor |
| `com.unity.services.tooling` | 1.4.1 | Access Control and Game Overrides |
| `com.unity.services.apis` | 1.1.1 | Generated REST clients for all UGS services |

- [Initialization Pattern](#initialization-pattern)
- [Package Map](#package-map)
- [Architecture — How Packages Combine](#architecture--how-packages-combine)
- [Core Services — Quick Reference](#core-services--quick-reference)
- [Asset Store Building Blocks](#asset-store-building-blocks)
- [Ready-Made Feature Blueprints](#ready-made-feature-blueprints)
- [Common Architecture Patterns](#common-architecture-patterns)
- [Validation](#validation)
- [Deployment Checklist](#deployment-checklist)
- [Detailed References](#detailed-references)

## Initialization Pattern

Every UGS game starts the same way. `com.unity.services.core` must initialize first, then the player signs in:

```csharp
using Unity.Services.Core;
using Unity.Services.Authentication;

await UnityServices.InitializeAsync();
await AuthenticationService.Instance.SignInAnonymouslyAsync();
// All other services are now ready
```

After `InitializeAsync()` completes, service singletons (e.g. `CloudSaveService.Instance`, `CloudCodeService.Instance`) are available.

## Package Map

### Foundation

| Package | Purpose | Singleton / Entry Point |
|---|---|---|
| **Core** | Initialization, dependency graph, component registry | `UnityServices.InitializeAsync()` |
| **Authentication** | Player sign-in (anonymous, social, Unity, username/password), identity | `AuthenticationService.Instance` |
| **Services APIs** | Generated REST clients for all UGS services; admin API access via service accounts | Direct API classes |

### Player Data and Configuration

| Package | Purpose | Singleton / Entry Point |
|---|---|---|
| **Cloud Save** | Per-player key-value data (Default, Public, Protected) and game-wide Custom data | `CloudSaveService.Instance.Data.Player` / `.Data.Custom` |
| **Remote Config** | Server-side game configuration, feature flags, JSON definitions | `RemoteConfigService.Instance` |
| **Economy** | Virtual currencies, inventory items, purchases, stores | `EconomyService.Instance` |

### Server Logic and Security

| Package | Purpose | Singleton / Entry Point |
|---|---|---|
| **Cloud Code** | Server-authoritative C# modules for trusted writes and validation | `CloudCodeService.Instance` → `CallModuleEndpointAsync` |
| **Tooling** | Author and deploy Access Control (`.ac`) and Game Overrides (`.ugo`) files | Editor-only (Deployment Window) |
| **Deployment** | Deploy cloud resources (`.rc`, `.ac`, `.ccmr`, `.lb`, etc.) from the Unity Editor | Editor-only (Services > Deployment) |

### Social and Competitive

| Package | Purpose | Singleton / Entry Point |
|---|---|---|
| **Multiplayer** | Sessions, matchmaking, lobbies. Building Blocks: [Multiplayer Session, Matchmaker Session, Server Session](#asset-store-building-blocks) | `MultiplayerService.Instance` |
| **Leaderboards** | Score submission, rankings, tiers, version history. Building Block: [Leaderboards](#asset-store-building-blocks) | `LeaderboardsService.Instance` |

### Telemetry

| Package | Purpose | Singleton / Entry Point |
|---|---|---|
| **Analytics** | Custom events, standard events, consent management | `AnalyticsService.Instance` |

## Architecture — How Packages Combine

```
                    UnityServices.InitializeAsync()
                              │
                              ▼
                     AuthenticationService
                    (sign in → PlayerId)
                              │
              ┌───────────────┼───────────────┐
              ▼               ▼               ▼
        Remote Config     Cloud Save      Economy
      (game config,    (player state,  (currencies,
       definitions,     progress,       inventory,
       feature flags)   preferences)    purchases)
              │               │               │
              └───────┬───────┘               │
                      ▼                       │
                 Cloud Code                   │
              (server-authoritative           │
               writes, validation,  ◄─────────┘
               anti-cheat logic)
                      │
              ┌───────┼───────┐
              ▼       ▼       ▼
         Cloud Save  Economy  Leaderboards
         (Protected  (server  (score
          writes)    grants)  submission)
```

**Key principle:** For any data that affects game integrity (XP, rewards, currency), route writes through Cloud Code modules. Direct client writes are only appropriate for non-sensitive data (preferences, display settings).

## Core Services — Quick Reference

### Authentication

**Package:** `com.unity.services.authentication` (>= 3.6.1)

Handles player identity. Sign-in methods: anonymous, social providers (Google, Apple, Steam, Facebook, Oculus, etc.), Unity browser, username/password, and device code flow.

After sign-in: `PlayerId` and `PlayerName` are available. All sign-in methods fire the `SignedIn` event. `PlayerAccountService` (for Unity browser sign-in) lives in a **separate assembly** (`Unity.Services.Authentication.Pla

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 088088a

Download folder ↗
git clone https://github.com/unity-technologies/skills
git -C skills checkout 088088af666d

The author documents no install command, so this uses the repository directly. Our verdict covers commit 088088af666d only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 088088af666d

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/unity-technologies/build-live-game/badge.svg)](https://modelsatlas.com/skills/unity-technologies/build-live-game/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/unity-technologies/build-live-game/badge.svg)](https://modelsatlas.com/skills/unity-technologies/build-live-game/)

Questions about build-live-game

What does the build-live-game skill do?
A collection of reusable skills for AI coding agents — prompts, slash commands, and tools built for Unity workflows
Is build-live-game safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can build-live-game access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (088088af666d), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.