Agent skill · Audited from source

levelplay-unity-integration

skill · unity-technologies/skillsNOASSERTION licenceAudited 22 Oct 2026 · source 088088af666d

★ 1,128pushed today
!CAUTIONGrade B · 89/100 · 2 findings · 088088a
1,128repo stars · whole unity-technologies/skills

Is it safe? With care — CAUTION, 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. The audit raised 2 findings, 1 critical or high. What it does: Integrates the LevelPlay ad mediation SDK via the Ads Mediation package. Use when the user asks about adding rewarded, interstitial, or banner ads, mediation or ad privacy setup, Android or iOS ad dependency build…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “levelplay-unity-integration (unity-technologies/skills)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/unity-technologies/levelplay-unity-integration

Trust audit

Audit 0.4.1 · source read 22 Oct 2026

Trust score89/100!CAUTION B
0 critical1 high1 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. 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 directivesFAIL2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

HIGHPrompt injectionprompt.credential_read · SKILL.md:125
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Before initializing LevelPlay, collect credentials from the LevelPlay dashboard.
Why
asks the agent to read credentials
Fix
—
MEDIUMPrompt injectionreview.instruction_override · SKILL.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
do not describe, characterize, or make claims about competitor products
Why
The text instructs the agent to avoid discussing or describing competitor products, which could override the user's explicit request for comparative information.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha 088088af666d · 22 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/levelplay-unity-integrationThe 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: Integrates the LevelPlay ad mediation SDK via the Ads Mediation package. Use when the user asks about adding rewarded, interstitial, or banner ads, mediation or ad privacy setup, Android or iOS ad dependency build…

---
name: levelplay-unity-integration
description: Integrates the LevelPlay ad mediation SDK via the Ads Mediation package. Use when the user asks about adding rewarded, interstitial, or banner ads, mediation or ad privacy setup, Android or iOS ad dependency build failures, or migrating from Unity Ads or IronSource APIs.
---

# LevelPlay Unity package/SDK Integration

Base editor-side checks on the actual project rather than assumptions — read the project files, or ask the user to confirm in the Editor. The C# scripts generated in this skill are MonoBehaviour files for the user to save to their project, not for inline execution.

This skill covers the LevelPlay integration path only; it does not cover other mediation SDKs. If the user explicitly asks about alternatives, acknowledge that alternatives exist and point them to those vendors' own documentation — do not describe, characterize, or make claims about competitor products.

Follow the steps and provide only the files and configurations described in this skill. Do not proactively add steps, create files, or make recommendations based on general knowledge. If the user asks a question outside the scope of this skill, check the skill and reference files first to confirm it is not covered. If it is not, use general knowledge to respond, but do not incorporate additional steps or files into the integration workflow as a result.

Follow the integration workflow sequentially, one step at a time. Ask only the questions for the current step — do not gather information for future steps in advance. Wait for the user's response at each checkpoint before proceeding.

LevelPlay is Unity's ad mediation platform: it connects your game to multiple ad networks simultaneously and runs a unified auction across multiple ad networks and bidders to maximize competition for each impression. This guide walks you through the full integration: installing the SDK, configuring dependencies for Android and iOS, initializing LevelPlay in your project, and implementing rewarded, interstitial, and banner ads. If you already have part of this set up, you can skip ahead to the relevant step.

**This SKILL.md is the workflow spine. It keeps the decisions, checkpoints, and exact questions; longer code, full API detail, and edge cases live in `references/` and are linked from the relevant step. Read the linked reference when you reach that step — do not answer from general knowledge instead.**

## Integration Workflow

### 0. New Integration or Migration?

Ask: "Are you starting a new LevelPlay integration, migrating an existing one (from an older SDK version or from Unity Ads), or troubleshooting an existing setup?"

- **New integration**: proceed to Step 1.
- **Migration** (SDK upgrade, replacing IronSource.Agent APIs, migrating from Unity Ads, or fixing a Maven Central Android build failure): Read `references/migration-sdk-9.md`. Ask which of the five scenarios applies — A = SDK upgrade, B = init API migration, C = ad unit API migration, D = Maven Central build failure, E = Unity Ads migration — then follow the matching scenario. After applying all code changes, work through the Migration Completeness Checklist (section C5 of the reference) — it catches requirements that a line-by-line translation misses because the legacy code had no equivalent line. Then ask the user to check the Unity console for compilation errors, and fix any that appear before presenting results. Do not block or keep retrying if you cannot see the console: list the files you changed, say what to look for, and continue.
- **Troubleshooting or adding to an existing setup** (ATT, GDPR, ILRD, Test Suite, build errors on a fresh integration, or adding a feature to an already-working integration): Identify what the user needs and go directly to the relevant step or reference from "When to Read Detailed References."

### 1. Verify Unity Environment

Check that the user is working in a Unity project by verifying Assets/ and ProjectSettings/ directories exist. If not in a Unity project, instruct the user to navigate to their Unity project directory. If those directories are not found but the user believes they are in the right place, ask: "It looks like you may not be at your project root — can you navigate to the top-level folder of your Unity project and confirm you can see Assets/ and ProjectSettings/ there?"

### 2. Understand Business Goals

Before implementing ad units, determine the user's optimization priorities to recommend the appropriate ad unit strategy. Ask:

**"What's your primary optimization goal?"**
- **Revenue-focused**: Maximize ad revenue and impression opportunities
- **UX-focused**: Prioritize gameplay flow and user satisfaction  
- **Balanced**: Optimize for both revenue and UX
- **Not sure yet**: Default to Balanced and proceed. At Step 8, briefly note you're using Balanced since they were unsure, and invite them to indicate a different preference now that they've seen the format options.

Record this answer for later strategy recommendation in Step 8.

### 3. Install LevelPlay SDK via UPM

**If the SDK looks already installed:** do not take that on trust, and do not ask the user to read
the Package Manager window for you. Read `Packages/packages-lock.json` and look for
`com.unity.services.levelplay`. If it is there, say which version resolved and proceed to Step 4.
If it is not, it is not installed, whatever the conversation so far has assumed: continue with the
install below.

Guide through installing the LevelPlay Unity package using Unity Package Manager:

1. Open Unity → Window > Package Manager
2. Select Unity Registry dropdown or Services tab
3. In the Package Manager search bar, type **Ads Mediation**
4. Confirm the package name matches exactly: the correct package is titled **Ads Mediation**. Do not install either of these packages:
   - **Ads IAP Mediation Adaptor** (a separate in-app purchases package, not the LevelPlay SDK)
   - **Advertisement Legacy** (a deprecated 

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 ↗
npx skills add Unity-Technologies/skills

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 088088af666d only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 088088af666d

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/unity-technologies/levelplay-unity-integration/badge.svg)](https://modelsatlas.com/skills/unity-technologies/levelplay-unity-integration/)

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: CAUTION B](https://modelsatlas.com/skills/unity-technologies/levelplay-unity-integration/badge.svg)](https://modelsatlas.com/skills/unity-technologies/levelplay-unity-integration/)

Questions about levelplay-unity-integration

What does the levelplay-unity-integration skill do?
A collection of reusable skills for AI coding agents — prompts, slash commands, and tools built for Unity workflows
Is levelplay-unity-integration safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can levelplay-unity-integration access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does levelplay-unity-integration work with?
Its documentation mentions claude-code, copilot and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (088088af666d), read on 2026-10-22. 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.