mcp-server
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform integration testing. Specifically, it provides
curlcommands to verify the functionality of the newly created MCP endpoints. - [DATA_EXFILTRATION]: The skill performs queries against sensitive ServiceNow tables such as
sys_oauth_entity,sys_security_acl, andsys_properties. These actions are necessary to configure the authentication layer and security policies for the MCP server and do not involve exfiltrating data to external domains. - [SAFE]: The implementation instructions prioritize security by including a dedicated section on input validation (Step 8), which covers table allowlisting, query sanitization to prevent script injection, and field-level filtering for sensitive data.
Audit Metadata