unity-optimization

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests project-specific data such as asset names, file paths, and filters to perform batch modifications. Although this is a standard capability for development tools, it represents a surface where untrusted project content could influence agent behavior.
  • Ingestion points: Parameters like filter, name, and path in SKILL.md allow the agent to target specific assets and GameObjects for optimization actions.
  • Boundary markers: None identified. There are no explicit instructions or delimiters used to isolate these identifiers from the agent's logic.
  • Capability inventory: The skill can modify local Unity asset files (Textures, Audio, Meshes) and change scene component configurations (StaticEditorFlags, LODGroups).
  • Sanitization: Not documented in the skill instructions; validation is assumed to be handled by the underlying Unity API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:59 AM