skills/serac-labs/serac/csdm-modeling/Gen Agent Trust Hub

csdm-modeling

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of technical documentation and instructions for modeling ServiceNow CMDB records according to the Common Service Data Model (CSDM). No malicious behavior is present.
  • [SAFE]: The skill identifies and provides workarounds for existing bugs and logic errors in the platform's ServiceNow tools, such as incorrect data handling in snow_impact_analysis and schema mapping errors in snow_cmdb_search.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The instructions focus on maintaining data integrity within a ServiceNow instance.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides guidance on ingesting and processing data from ServiceNow tables (e.g., sys_db_object, cmdb_ci_service). It explicitly recommends validation steps, such as searching before creating records and verifying field names using snow_discover_table_fields, to mitigate the risk of processing incorrect or improperly structured data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:15 PM
Security Audit — agent-trust-hub — csdm-modeling