major-incident

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill implements standard IT Service Management (ITSM) workflows using ServiceNow MCP tools and REST APIs for their intended operational purposes.
  • [SAFE]: All external references point to trusted documentation sources including official ServiceNow docs, ITIL.org, Google SRE, and PagerDuty.
  • [SAFE]: The skill includes a surface for indirect prompt injection as it processes incident work notes, but it does so within a structured framework and does not perform any dangerous operations on that data.
  • Ingestion points: Step 4.2 retrieves data from the sys_journal_field table in SKILL.md.
  • Boundary markers: None identified in the provided templates.
  • Capability inventory: Record creation and updates (SN-Create-Record, SN-Update-Record, SN-Add-Work-Notes) across SKILL.md.
  • Sanitization: Not explicitly documented in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — major-incident