contracts-query-enhancer

Warn

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the SN-Execute-Background-Script tool to run server-side JavaScript on a ServiceNow instance (Step 6, Example 3). This is a high-privilege operation that allows for arbitrary code execution within the target environment.
  • [REMOTE_CODE_EXECUTION]: The skill demonstrates dynamic script generation where natural language search intent is translated into JavaScript code (Step 6). This creates an attack surface for code injection if a user-supplied query can influence the structure or logic of the script executed via SN-Execute-Background-Script.
  • [DATA_EXFILTRATION]: The skill provides detailed procedures for accessing sensitive business data, including contract terms, financial values, and vendor obligations across multiple ServiceNow tables (ast_contract, clm_obligation). While intended for legitimate search, these patterns provide a framework for large-scale data harvesting.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — contracts-query-enhancer