deep-interactive
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and a configuration file intended to guide the AI in structuring educational content. It does not include any scripts or commands.
- [DATA_EXPOSURE]: There are no references to sensitive file paths, environment variables, or hardcoded credentials. No network operations (such as curl or wget) are present.
- [PROMPT_INJECTION]: The instructions focus entirely on course design (e.g., scene types, widget selection, and naming conventions) and do not attempt to override the agent's safety protocols or system instructions.
- [DYNAMIC_EXECUTION]: While the skill mentions a 'code' widget type, this refers to a visual component for the learner to interact with in the generated course, rather than code that the agent or the platform executes at runtime.
Audit Metadata