event-management

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection through the ingestion of external monitoring data.
  • Ingestion points: Raw data enters the system from external monitoring tools (Nagios, SCOM, etc.) into the em_event table.
  • Boundary markers: None identified in the provided JavaScript snippets for processing external strings.
  • Capability inventory: The skill uses snow_execute_script, snow_query_table, and snow_create_event (SKILL.md).
  • Sanitization: There is a try...catch block for JSON parsing, but no explicit escaping or sanitization when concatenating event fields like description.
  • [DYNAMIC_EXECUTION]: The skill demonstrates legitimate dynamic execution patterns required for ServiceNow automation.
  • Execution tool: The skill utilizes snow_execute_script to run ServiceNow GlideScript on the instance (SKILL.md).
  • Stored scripts: The skill provides examples of Advanced Scripts stored in database fields (em_event_rule.script) which are executed dynamically by the ServiceNow platform to process incoming events.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:15 PM
Security Audit — agent-trust-hub — event-management