unity-ai-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited unity-ai-audit (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Run get_ai_stack_summary with include_prompt_assets: true.
| Step | Tool | Why |
|---|---|---|
| 1 | get_ai_ml_package_inventory | Official Unity AI packages & versions |
| 2 | list_ml_model_assets | ONNX and other models in repo |
| 3 | list_ml_agents_training_configs | RL training YAMLs |
| 4 | find_ai_related_scripts | Code-level AI APIs |
| 5 | list_ai_prompt_or_config_assets | Prompt/RAG JSON or docs |
| 6 | get_build_size_estimate | Model weight in shipping build |
| 7 | get_release_readiness | Broken refs + cycles + large assets |
Call list_ai_skills then read_ai_skill for focused workflows:
unity-ml-agentsunity-sentis-inferenceunity-navmesh-npcunity-llm-integration## AI stack summary
- Packages: ...
- Models: N ONNX, ...
- Scripts: N files (top labels: ...)
- Training configs: ...
- Risks: secrets in client?, build size, missing packages~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.