spatial-design
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured design rules and production pipeline metrics for visionOS applications and immersive environments based on established industry standards. All referenced external resources point to official Apple developer videos and documentation at developer.apple.com.- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to its architecture for processing external application data combined with broad file-system capabilities.
- Ingestion points: The skill is explicitly intended for reviewing any visionOS app, window, or volume, utilizing tools such as Read, Glob, and Grep to ingest code and design files (SKILL.md).
- Boundary markers: There are no instructions or delimiters provided to ensure that the agent distinguishes between the ingested application content and the agent's core instructions.
- Capability inventory: The skill includes allowed-tools such as Write and Edit (SKILL.md), which grant the agent the ability to modify project files based on the untrusted data it analyzes.
- Sanitization: There are no mechanisms described for validating, escaping, or filtering the content retrieved from analyzed applications before it is processed by the agent.
Audit Metadata