csm-suggested-steps

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses established ServiceNow MCP tools and REST API endpoints to facilitate case management workflows. These operations are consistent with the stated purpose of assisting support agents.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface by ingesting untrusted historical data from past cases and work notes to generate suggestions.
  • Ingestion points: The skill reads from sn_customerservice_case, sys_journal_field, and interaction tables (SKILL.md).
  • Boundary markers: Absent; there are no specific instructions provided to the agent to disregard instructions found within the historical data.
  • Capability inventory: The skill has the ability to update records (SN-Update-Record) and execute shell commands (Bash).
  • Sanitization: No explicit sanitization or filtering of the retrieved historical content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:35 PM