vtex-io-masterdata
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill documentation describes network requests to official VTEX infrastructure domains such as api.vtex.com and vtexcommercestable.com.br. These are legitimate operations for the skill's purpose of managing Master Data and originate from the author's own services.
- [CREDENTIALS_UNSAFE]: Code and command-line examples use standard placeholders for authentication headers, such as {appKey} and {appToken}. No actual secrets, credentials, or private keys are hardcoded in the skill.
- [EXTERNAL_DOWNLOADS]: The skill references official VTEX development libraries, specifically @vtex/clients. These are standard dependencies for building applications on the VTEX IO platform.
- [PROMPT_INJECTION]: The instructions provide architectural constraints and decision rules for developers. These represent legitimate pedagogical content intended to guide agent behavior during solution design and do not attempt to bypass core AI safety guardrails.
- [COMMAND_EXECUTION]: The skill documentation includes curl commands intended for manual execution by developers for administrative tasks like schema lifecycle management. There are no patterns suggesting automated or malicious command execution.
Audit Metadata