unity-validation

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes project-specific data such as shader code and asset metadata which may contain untrusted strings.
  • Ingestion points: Data is gathered via skills like validate_scene, validate_shader_errors, and validate_project_structure.
  • Boundary markers: No explicit delimiters or instruction-blocking markers are defined for the ingested content.
  • Capability inventory: The skill set includes capabilities to delete empty folders and remove script components.
  • Sanitization: The documentation does not specify sanitization or validation of the ingested project data.
  • [COMMAND_EXECUTION]: The module includes functionality to modify the file system and project structure.
  • Evidence: The validate_cleanup_empty_folders and validate_fix_missing_scripts skills perform deletion of project artifacts when dryRun is disabled.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:00 AM