itsm-kb-generation

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses data from ServiceNow tables including incident, problem, and journal fields. This data access is a functional requirement for extracting resolution details to generate knowledge articles.
  • [COMMAND_EXECUTION]: The skill uses the SN-Execute-Background-Script tool to run server-side JavaScript on the ServiceNow instance for identifying candidates and reporting. The logic provided is consistent with the skill's administrative purpose.
  • [PROMPT_INJECTION]: The skill handles untrusted data from ServiceNow records (incident descriptions, work notes) to generate articles, creating an indirect prompt injection surface.
  • Ingestion points: Data is retrieved from the incident and sys_journal_field tables using SN-Get-Record and SN-Query-Table (SKILL.md).
  • Boundary markers: There are no explicit delimiters used when processing external record content into knowledge article templates.
  • Capability inventory: The skill can create and update database records and execute server-side scripts on the ServiceNow platform.
  • Sanitization: Ingested content from ServiceNow is used in the article generation process without explicit sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — itsm-kb-generation