unity-grid-level-editor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional content for Unity development. It prioritizes data integrity and isolation, explicitly warning against global save operations that could affect unrelated assets. No malicious patterns, obfuscation, or exfiltration attempts were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture for processing level data, which introduces an ingestion surface for untrusted external content.\n
- Ingestion points:
references/mechanics.mddescribes loading JSON datasets and ScriptableObject assets.\n - Boundary markers: The skill mandates fingerprint comparison to detect external edits and structural validation of candidates.\n
- Capability inventory: The system performs local asset writes and preview rendering using standard Unity APIs.\n
- Sanitization: Instructions include explicit structural validation and stable-ID uniqueness checks.
Audit Metadata