feedback-summarization

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill reads free-text feedback that outsiders can author at runtime from ServiceNow tables (e.g., sys_journal_field.value in sprint work_notes, and asmt_assessment_instance_question.string_value for survey responses) via SN-Query-Table/REST endpoints without requiring the agent to first select a specific item.