uloop-get-hierarchy
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from Unity scenes, creating a surface for indirect prompt injection where maliciously named GameObjects could influence the agent's behavior.
- Ingestion points: Unity project hierarchy data (GameObject names, paths, and components) accessed via the
uloop get-hierarchycommand. - Boundary markers: The output is returned as structured JSON, but no explicit instructions are provided to the agent to disregard potential natural language instructions embedded within that data.
- Capability inventory: The skill allows the agent to execute the
uloopCLI tool and specify arbitrary project paths using the--project-pathoption. - Sanitization: There is no evidence of sanitization or validation of the scene data before it is presented to the agent's context.
Audit Metadata