type-definition-creator
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions are task-oriented and do not contain patterns aimed at overriding behavior or bypassing constraints.
- [COMMAND_EXECUTION]: Shell commands are restricted to the official platform CLI (dxs) and the jq utility for standard configuration management tasks.
- [DATA_EXFILTRATION]: No sensitive data access or unauthorized external transmissions were identified. Operations are limited to the vendor's platform environment.
- [EXTERNAL_DOWNLOADS]: Data retrieval is conducted exclusively via official platform tools for the purpose of editing project configurations.
Audit Metadata