connect-ai-base
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a procedural guide for data discovery and SQL querying through a known enterprise integration platform (CData). All external links point to official documentation domains (docs.cloud.cdata.com).
- [COMMAND_EXECUTION]: The skill mentions invoking
connect-ai-onboarding-claude-codeor specific tools liketool_search,getCatalogs, andqueryData. These are standard MCP tool calls intended for the agent's interaction with the CData service and do not represent arbitrary or dangerous shell execution. - [DATA_EXPOSURE]: While the skill instructions involve querying databases (Salesforce, SQL Server, etc.), it emphasizes user-authorized connections, discovery tools (
getColumns), and safety best practices like usingLIMITon queries to prevent large data dumps.
Audit Metadata