csm-case-summarization
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the native Bash tool to execute HTTP GET requests via curl for interacting with ServiceNow REST API endpoints.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data from external records into its output.
- Ingestion points: Untrusted data enters the agent context from the
description,short_description,sys_journal_field(work notes and comments), andsys_email(subjects and bodies) tables in ServiceNow. - Boundary markers: The summary template in
SKILL.mdlacks clear delimiters or instructions to the model to treat the interpolated record data as untrusted content. - Capability inventory: The skill has access to the native
Bashtool and various ServiceNow MCP tools (SN-Query-Table,SN-Read-Record) for further system interaction. - Sanitization: No validation or sanitization of the content retrieved from the ServiceNow tables is specified before it is processed for summarization.
Audit Metadata