survey-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes free-text survey responses from the asmt_assessment_instance_question table without sanitization or boundary markers.
  • Ingestion points: Step 6 uses SN-Query-Table to fetch string_value content from survey response records.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between system instructions and user-provided survey content.
  • Capability inventory: The skill uses SN-Execute-Background-Script and SN-Add-Work-Notes, which provide significant interaction with the ServiceNow environment.
  • Sanitization: No sanitization or filtering of the retrieved survey comments is described in the procedure.
  • [COMMAND_EXECUTION]: The skill employs SN-Execute-Background-Script to run complex JavaScript snippets for data aggregation. This allows for arbitrary server-side script execution within the ServiceNow instance, which is a powerful capability intended for administrators but requiring caution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — survey-analysis