The Agent Skills Directory

[SAFE]: No evidence of malicious behavior, prompt injection, or unauthorized data access was found. The skill documentation explicitly identifies high-risk operations (such as object deletion in 'smart_replace_objects') and describes platform-level safety modes (Approval, Auto, Bypass) to manage these risks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided strings for querying component properties and specifying asset paths. While this represents a data ingestion surface, the documentation notes that the implementation performs semantic validation, such as rejecting invalid operators or unknown property names with 'SEMANTIC_INVALID' errors. This input processing is standard for the skill's primary purpose of Unity scene management.

unity-smart