data-classification

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the SN-Execute-Background-Script tool to run server-side JavaScript on a ServiceNow instance. This capability is used to perform administrative tasks including schema discovery and record scanning for sensitive data patterns.
  • [PROMPT_INJECTION]: The skill processes untrusted data from ServiceNow tables during PII/PHI discovery scans, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads content from incident.description, incident.comments, sc_req_item.special_instructions, and kb_knowledge.text fields to identify embedded sensitive data.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the scanning scripts.
  • Capability inventory: The skill environment includes tools for executing scripts (SN-Execute-Background-Script) and modifying records (SN-Create-Record, SN-Update-Record).
  • Sanitization: Content is matched against regular expressions without sanitization or filtering of the source text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — data-classification