Skills
skills/jmsktm/claude-settings/email-notifications/Gen Agent Trust Hub

email-notifications

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes logic for processing data from ServiceNow tables that may contain untrusted user content.
  • Ingestion points: ServiceNow record data from sys_journal_field, sys_attachment, and incident tables (SKILL.md).
  • Boundary markers: Absent in the provided code templates.
  • Capability inventory: The skill uses the snow_execute_script_with_output tool and internal GlideRecord API to query and process data.
  • Sanitization: Code examples use basic field retrieval and truncation (substring) but do not include explicit sanitization of data before inclusion in email templates.
  • [DYNAMIC_EXECUTION]: The skill provides educational templates for ServiceNow server-side JavaScript (ES5/Rhino) to be used within the platform's native notification and scripting engine.
  • [SAFE]: The tools requested in the metadata (snow_configure_email, snow_query_table, snow_find_artifact, snow_execute_script_with_output) are restricted to ServiceNow-specific development tasks and are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 06:35 AM
Security Audit — agent-trust-hub — email-notifications