godot-interactive
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to malicious instructions embedded in the Godot project files it processes.
- Ingestion points: Tools such as godot_read_scene, godot_read_script, and godot_read_shader ingest content directly from the local project workspace into the agent's context.
- Boundary markers: The instructions lack delimiters or explicit warnings to ignore natural language instructions found within file content or comments.
- Capability inventory: The agent has high-privilege access, including executing code in the editor, writing files, and launching runtime processes.
- Sanitization: There is no requirement for content sanitization or validation of the ingested file data.
- [DYNAMIC_EXECUTION]: The skill facilitates the generation and execution of code within the editor environment.
- Evidence: The tool godot_editor_execute_gdscript is used to run dynamically constructed GDScript snippets for editor diagnostics and setup.
- [COMMAND_EXECUTION]: The skill manages the execution of external engine processes.
- Evidence: The godot_editor_run_scene tool triggers the execution of the Godot engine runtime to test project behavior.
Audit Metadata