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 curl commands 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, and sys_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
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — mcp-server