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), and sys_email (subjects and bodies) tables in ServiceNow.
  • Boundary markers: The summary template in SKILL.md lacks 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 Bash tool 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
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:35 PM