field-service

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code or patterns detected. The skill correctly implements ServiceNow development workflows using standard GlideRecord operations for Field Service Management.- [COMMAND_EXECUTION]: The skill utilizes the snow_execute_script_with_output tool to run ServiceNow-specific scripts (ES5). This behavior is intended for testing and automating tasks within the ServiceNow development environment.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing data from ServiceNow tables (wm_order, wm_task) that could contain untrusted input.
  • Ingestion points: ServiceNow record data accessed via snow_query_table.
  • Boundary markers: None implemented in the provided script examples.
  • Capability inventory: Includes snow_execute_script_with_output and snow_query_table.
  • Sanitization: No input sanitization or validation is demonstrated in the processing examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:34 AM
Security Audit — agent-trust-hub — field-service